Find B2B leads on LinkedIn that match your ICP, with verified facts and a first message for each.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional. A catchy-me API key from Settings (catchy_...), sent as a Bearer token. Without it, clients that support MCP OAuth sign in through the browser when an account tool is called; public tools work without sign-in.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Records that the user accepted the current Terms of Use (https://catchy-me.com/terms) and took note of the current Privacy Policy (https://catchy-me.com/privacy). Use it when a tool answered legal_pending: first show the user both links and ask whether they accept the updated Terms; call it with confirm=true ONLY after the user explicitly agreed — never on your own. The other tools work again after it. The user may instead accept them in the Catchy web app. [REST: (as POST /api/legal/accept)]
The user read the links and explicitly agreed.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http catchy-me https://app.catchy-me.com/mcp
Headers
Authorization (optional, not in the config above): Optional. A catchy-me API key from Settings (catchy_...), sent as a Bearer token. Without it, clients that support MCP OAuth sign in through the browser when an account tool is called; public tools work without sign-in.Records that the user accepted the current Terms of Use (https://catchy-me.com/terms) and took note of the current Privacy Policy (https://catchy-me.com/privacy). Use it when a tool answered legal_pending: first show the user both links and ask whether they accept the updated Terms; call it with confirm=true ONLY after the user explicitly agreed — never on your own. The other tools work again after it. The user may instead accept them in the Catchy web app. [REST: (as POST /api/legal/accept)]
| Argument | Type | Description |
|---|---|---|
| confirm* | boolean | The user read the links and explicitly agreed. |
{
"type": "object",
"required": [
"confirm"
],
"properties": {
"confirm": {
"type": "boolean",
"const": true,
"description": "The user read the links and explicitly agreed."
}
},
"additionalProperties": false
}Replaces the person's messages with that variant (free); result_id and expected_result_revision from get_outreach_lead. [REST: POST /api/tasks/{id}/outreach/leads/{cid}/candidates/{candidate_id}/apply]
| Argument | Type | Description |
|---|---|---|
| cid* | string | The person's id (cid) from list_leads. |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| result_id | string | |
| candidate_id* | string | |
| expected_result_revision | integer |
{
"type": "object",
"required": [
"task_id",
"cid",
"candidate_id"
],
"properties": {
"cid": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The person's id (cid) from list_leads."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"result_id": {
"type": "string",
"maxLength": 80
},
"candidate_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"expected_result_revision": {
"type": "integer",
"minimum": 0
}
},
"additionalProperties": false
}Stops the renewal of a LavaTop subscription: the plan stays until the period's end and the credits stay on the balance after it. Ask the user to confirm and pass confirm=true. [REST: POST /api/billing/subscription/cancel]
| Argument | Type | Description |
|---|---|---|
| confirm* | boolean |
{
"type": "object",
"required": [
"confirm"
],
"properties": {
"confirm": {
"type": "boolean",
"const": true
}
},
"additionalProperties": false
}What Catchy is and how it works: lead search with facts and AI outreach, plans, briefs and credits, how to connect this MCP server (OAuth or an API key), how an agent signs up by itself, and the links to the Terms of Use and the Privacy Policy. No sign-in needed.
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}Confirms the registration with the emailed code and the signup_token of sign_up, and returns an API key for this MCP server (shown once). [REST: POST /api/auth/register/verify]
| Argument | Type | Description |
|---|---|---|
| code* | string | |
| lang | string | The account's language (messages, the texts of its searches). Default en. |
| email* | string | |
| key_days | integer | null | Lifetime of the key in days; null = no limit. Default 365. |
| key_name | string | Name of the API key in Settings (default «MCP agent»). |
| key_access | string | |
| signup_token* | string |
{
"type": "object",
"required": [
"email",
"code",
"signup_token"
],
"properties": {
"code": {
"type": "string",
"maxLength": 20,
"minLength": 4
},
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"description": "The account's language (messages, the texts of its searches). Default en."
},
"email": {
"type": "string",
"maxLength": 254,
"minLength": 3
},
"key_days": {
"type": [
"integer",
"null"
],
"maximum": 1825,
"minimum": 1,
"description": "Lifetime of the key in days; null = no limit. Default 365."
},
"key_name": {
"type": "string",
"maxLength": 60,
"minLength": 1,
"description": "Name of the API key in Settings (default «MCP agent»)."
},
"key_access": {
"enum": [
"full",
"read"
],
"type": "string",
"default": "full"
},
"signup_token": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{20,100}$"
}
},
"additionalProperties": false
}«Продолжить поиск»: a finished or stopped search goes on for `more` more leads with the same requirements (no new brief). SPENDS CREDITS: quote_search(leads=more) first, show the price, and after the user's yes pass its credits_high as confirm_credits. Returns at once; poll get_search. [REST: POST /api/tasks/{id}/more]
| Argument | Type | Description |
|---|---|---|
| more* | integer | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| stop_at_target | boolean | |
| confirm_credits* | integer | The price in credits the matching quote returned, shown to the user and confirmed by them. |
{
"type": "object",
"required": [
"task_id",
"more",
"confirm_credits"
],
"properties": {
"more": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"stop_at_target": {
"type": "boolean",
"default": true
},
"confirm_credits": {
"type": "integer",
"minimum": 0,
"description": "The price in credits the matching quote returned, shown to the user and confirmed by them."
}
},
"additionalProperties": false
}A started search: pause, resume, stop (the leads found are kept and charged), or continue — the answer to a search that asks about a higher price (status asking): it SPENDS the extra credits of get_search's `ask.continue_credits`; show them and pass them as confirm_credits after the user's yes. [REST: POST /api/tasks/{id}/control]
| Argument | Type | Description |
|---|---|---|
| action* | string | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| confirm_credits | integer | The price in credits the matching quote returned, shown to the user and confirmed by them. |
{
"type": "object",
"required": [
"task_id",
"action"
],
"properties": {
"action": {
"enum": [
"pause",
"resume",
"stop",
"continue"
],
"type": "string"
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"confirm_credits": {
"type": "integer",
"minimum": 0,
"description": "The price in credits the matching quote returned, shown to the user and confirmed by them."
}
},
"additionalProperties": false
}Creates a new lead search («поиск лидов») from the onboarding answers and starts compiling its requirements (~1-2 minutes; nothing is charged in credits, but it spends the onboarding's brief if no assistant did). Then poll get_search every 20-30 s until status is `ready`, review the spec with the user (get_search detail=spec), and only then quote and run it. company and icp are required. [REST: POST /api/tasks]
| Argument | Type | Description |
|---|---|---|
| icp* | string | Whom to find: the customer profile (step 3). |
| goal | string | What the outreach should achieve (step 2). |
| company* | string | What the user's company does (step 1). |
| language | string | Language of the outreach messages (default english). |
| source_task | string | The earlier onboarding this one was filled from (get_onboarding_prefill). |
| exclude_urls | array | LinkedIn profile links of people to leave out. |
| exclude_scope | string | From those searches: everyone analysed (all) or only leads. |
| exclude_tasks | array | Earlier searches whose people to leave out. |
Deletes a search with its leads and outreach; a running one is stopped first. Nothing is refunded and it cannot be undone. Ask the user to confirm and pass confirm=true. [REST: DELETE /api/tasks/{id}]
| Argument | Type | Description |
|---|---|---|
| confirm* | boolean | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id",
"confirm"
],
"properties": {
"confirm": {
"type": "boolean",
"const": true
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}After a search: moves chosen fit people to partial («в частично подходящие»), e.g. the user disagrees with the verdict. Free, at once. [REST: POST /api/tasks/{id}/demote]
| Argument | Type | Description |
|---|---|---|
| cids* | array | Person ids (cid) from list_leads. |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id",
"cids"
],
"properties": {
"cids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"maxItems": 300,
"minItems": 1,
"description": "Person ids (cid) from list_leads."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}The criteria revision («Изменить критерии»): while a search asks about a higher price, or when a finished search ran out of people, works out which criteria hold it back and proposes changes, each combination with its price in credits and the leads it may give. Takes up to ~75 s. Then revise_search with the chosen proposal ids. [REST: POST /api/tasks/{id}/revise/diagnose]
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}Before the run: the counter-signals («контрсигналы») that make a lead partial or a miss. action=remove or restore. [REST: POST /api/tasks/{id}/counter-signals/{sid}/remove|restore]
| Argument | Type | Description |
|---|---|---|
| action* | string | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| version | integer | The spec version from get_search (optional: protects against an edit made meanwhile in the web). |
| signal_id* | string |
{
"type": "object",
"required": [
"task_id",
"signal_id",
"action"
],
"properties": {
"action": {
"enum": [
"remove",
"restore"
],
"type": "string"
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"version": {
"type": "integer",
"minimum": 0,
"description": "The spec version from get_search (optional: protects against an edit made meanwhile in the web)."
},
"signal_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
}
},
"additionalProperties": false
}Before the run: action=add (a new requirement in words; an AI call adds it), edit (new wording and/or role / standard of criterion_id), remove («Неверно»: drop it; `confirm` true when the answer warned that it is the only job-title criterion), restore («Вернуть»: undo the last change of it). The estimate is counted again. [REST: POST /api/tasks/{id}/criteria, POST /api/tasks/{id}/criteria/{cid}/edit|remove|restore]
| Argument | Type | Description |
|---|---|---|
| role | string | |
| text | string | |
| action* | string | |
| confirm | boolean | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| version | integer | The spec version from get_search (optional: protects against an edit made meanwhile in the web). |
| standard | string | |
| criterion_id | string |
{
"type": "object",
"required": [
"task_id",
"action"
],
"properties": {
"role": {
"enum": [
"required",
"plus"
],
"type": "string"
},
"text": {
"type": "string",
"maxLength": 1000,
"minLength": 1
},
"action": {
"enum": [
"add",
"edit",
"remove",
"restore"
],
"type": "string"
},
"confirm": {
"type": "boolean"
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"version": {
"type": "integer",
"minimum": 0,
"description": "The spec version from get_search (optional: protects against an edit made meanwhile in the web)."
},
"standard": {
"enum": [
"inference",
"explicit"
],
"type": "string"
},
"criterion_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
}
},
"additionalProperties": false
}Saves the user's own text of one message step (free). result_id and expected_revision from get_outreach_lead protect against an edit made meanwhile. [REST: PATCH /api/tasks/{id}/outreach/leads/{cid}/steps/{step_id}]
| Argument | Type | Description |
|---|---|---|
| cid* | string | The person's id (cid) from list_leads. |
| text* | string | |
| step_id* | string | The step id of the message (get_outreach_lead steps[].step_id). |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| result_id | string | |
| expected_revision | integer |
{
"type": "object",
"required": [
"task_id",
"cid",
"step_id",
"text"
],
"properties": {
"cid": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The person's id (cid) from list_leads."
},
"text": {
"type": "string",
"maxLength": 3000,
"minLength": 1
},
"step_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The step id of the message (get_outreach_lead steps[].step_id)."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"result_id": {
"type": "string",
"maxLength": 80
},
"expected_revision": {
"type": "integer",
"minimum": 0
}
},
"additionalProperties": false
}Before the run: the pains («боли») the search looks for in a lead's facts. action=edit (new text of pain_id), remove, restore. [REST: POST /api/tasks/{id}/pains/{pid}/edit|remove|restore]
| Argument | Type | Description |
|---|---|---|
| text | string | |
| action* | string | |
| pain_id* | string | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| version | integer | The spec version from get_search (optional: protects against an edit made meanwhile in the web). |
{
"type": "object",
"required": [
"task_id",
"pain_id",
"action"
],
"properties": {
"text": {
"type": "string",
"maxLength": 1000,
"minLength": 1
},
"action": {
"enum": [
"edit",
"remove",
"restore"
],
"type": "string"
},
"pain_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"version": {
"type": "integer",
"minimum": 0,
"description": "The spec version from get_search (optional: protects against an edit made meanwhile in the web)."
}
},
"additionalProperties": false
}Before the run (status ready): change the role of criteria (required = must be proven, plus = a bonus) and how strictly they are proven (inference = may be inferred, explicit = needs an explicit source; dearer), and the order of the sources. No AI call; the estimate is counted again. Needs a plan (or credits). [REST: PATCH /api/tasks/{id}/spec]
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| version | integer | The spec version from get_search (optional: protects against an edit made meanwhile in the web). |
| criteria | array | |
| source_order | array |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"version": {
"type": "integer",
"minimum": 0,
"description": "The spec version from get_search (optional: protects against an edit made meanwhile in the web)."
},
"criteria": {
"type": "array",
"items": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"role": {
"enum": [
"required",
"plus"
],
"type": "string"
},
"standard": {
"enum": [
"inference",
"explicit"
],
"type": "string"
}
},
"additionalProperties": false
},
"maxItems": 50,
"minItems": 1
},
"source_order": {
"type": "array",
"items": {
"enum": [
"posts",
"site_pages",
"third_party"
],
"type": "string"
},
"maxItems": 3
}
},
"additionalProperties": false
}Correct the sender's card the analysis made (name, role, company, voice = how they write, summary, background, interests). [REST: PATCH /api/tasks/{id}/outreach/sender/card]
| Argument | Type | Description |
|---|---|---|
| name | string | |
| role | string | |
| voice | string | |
| company | string | |
| summary | string | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| interests | array | |
| background | array | |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"name": {
"type": "string",
"maxLength": 600
},
"role": {
"type": "string",
"maxLength": 600
},
"voice": {
"type": "string",
"maxLength": 600
},
"company": {
"type": "string",
"maxLength": 600
},
"summary": {
"type": "string",
"maxLength": 600
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"interests": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200
},
"maxItems": 20
},
"background": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200
},
"maxItems": 20
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
}
},
"additionalProperties": false
}A download link for the whole outreach as one Excel sheet (every person with the messages by touch, the route, the facts). Works for one hour without signing in; give it to the user. [REST: GET /api/tasks/{id}/outreach/export.xlsx (signed link /api/dl/{token})]
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}A download link for the search's leads as Excel (xlsx) or PDF: chosen kinds (default fit and partial), with the facts and the brief. The link works for one hour without signing in; give it to the user. [REST: GET /api/tasks/{id}/export.xlsx|pdf?kinds= (signed link /api/dl/{token})]
| Argument | Type | Description |
|---|---|---|
| kinds | array | |
| format | string | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"kinds": {
"type": "array",
"items": {
"enum": [
"fit",
"partial",
"miss"
],
"type": "string"
},
"maxItems": 3,
"minItems": 1,
"uniqueItems": true
},
"format": {
"enum": [
"xlsx",
"pdf"
],
"type": "string",
"default": "xlsx"
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}When the site cannot be read: a saved page (HTML), a PDF or a text file -> its text, to describe the company with suggest_company_description(text=...). Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief and may call each assistant once); pass the returned onboarding_id to the next calls and to create_search. [REST: POST /api/assist/site_file]
| Argument | Type | Description |
|---|---|---|
| file_name* | string | The file's name with its extension. |
| data_base64* | string | The file's bytes, base64. |
| onboarding_id | string | The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search. |
{
"type": "object",
"required": [
"file_name",
"data_base64"
],
"properties": {
"file_name": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "The file's name with its extension."
},
"data_base64": {
"type": "string",
"minLength": 4,
"description": "The file's bytes, base64."
},
"onboarding_id": {
"type": "string",
"pattern": "^[A-Za-z0-9-]{8,64}$",
"description": "The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search."
}
},
"additionalProperties": false
}The signed-in Catchy account: name, email, language, plan («тариф»: code, status, period end), briefs («брифы») left this period and when they renew, the free brief, the balance in whole credits (available = balance minus holds of running work) and the search limits (max leads per search). Call it first to know what the user can do: starting a search or an outreach needs a plan or credits, and each new setup spends one brief. [REST: GET /api/account, GET /api/config]
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The account's balance lines, newest first: top-ups, grants and charges (search, facts on request, outreach) in whole credits, with the search each charge was for. [REST: GET /api/account/balance/history]
| Argument | Type | Description |
|---|---|---|
| limit | integer |
{
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "integer",
"default": 50,
"maximum": 200,
"minimum": 1
}
},
"additionalProperties": false
}One person of a search: the profile card, the company, the verdict and why they fit, each criterion's status with how it was checked, and the facts found (dated, with source links) — the material for a personal message. [REST: GET /api/tasks/{id}/candidates/{cid}]
| Argument | Type | Description |
|---|---|---|
| cid* | string | The person's id (cid) from list_leads. |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id",
"cid"
],
"properties": {
"cid": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The person's id (cid) from list_leads."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}A finished AI variant of a person's messages that was not applied because the text was edited meanwhile (its id from get_outreach_lead). [REST: GET /api/tasks/{id}/outreach/leads/{cid}/candidates/{candidate_id}]
| Argument | Type | Description |
|---|---|---|
| cid* | string | The person's id (cid) from list_leads. |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| candidate_id* | string |
{
"type": "object",
"required": [
"task_id",
"cid",
"candidate_id"
],
"properties": {
"cid": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The person's id (cid) from list_leads."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"candidate_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
}
},
"additionalProperties": false
}The answers of an earlier onboarding (company, goal, icp, language) to reuse in create_search; pass its id as source_task there too, so the search plan made then is reused when the brief stays the same. [REST: GET /api/onboardings/{id}]
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}The outreach («Рассылка») of a finished search: the campaign (sender with its card, essence = offer / ask / tone / rules / language, the accounts, counts, the current generation, credits charged) and the fit people with their state (paginated), plus what to do next (`next`). [REST: GET /api/tasks/{id}/outreach]
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| offset | integer | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"limit": {
"type": "integer",
"default": 25,
"maximum": 100,
"minimum": 1
},
"offset": {
"type": "integer",
"default": 0,
"minimum": 0
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}One person of the outreach: the messages by step (network, kind, text, character limit, hook and the fact it uses, the post of a comment), the route and why, the findings of the research with sources, contacts. step_id, result_id and the revision are what the edit, rewrite and variant tools need. [REST: GET /api/tasks/{id}/outreach/leads/{cid}]
| Argument | Type | Description |
|---|---|---|
| cid* | string | The person's id (cid) from list_leads. |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id",
"cid"
],
"properties": {
"cid": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The person's id (cid) from list_leads."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}The status of a payment order made by subscribe: pending, paid, failed, expired, cancelled. When paid, get_account shows the plan and credits. [REST: GET /api/billing/orders/{id}]
| Argument | Type | Description |
|---|---|---|
| order_id* | string | The order id from subscribe. |
{
"type": "object",
"required": [
"order_id"
],
"properties": {
"order_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The order id from subscribe."
}
},
"additionalProperties": false
}One search: status, progress, counts, credits charged, the estimate (price examples), what to do next (`next`); for a search that asks about a higher price, the question (`ask`). detail=spec adds the requirements as the review screen shows them (criteria with ids, pains, counter-signals, the search method and its options, veins); detail=full adds the brief in full. Poll it while a search compiles or runs. [REST: GET /api/tasks/{id} (+ GET /api/tasks while it runs, GET /api/tasks/{id}/snapshot while it asks)]
| Argument | Type | Description |
|---|---|---|
| detail | string | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"detail": {
"enum": [
"summary",
"spec",
"full"
],
"type": "string",
"default": "summary"
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}A finished search's funnel in plain words: how many people were seen, checked, rejected and why, and how many became leads. [REST: GET /api/tasks/{id}/funnel]
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}The requirements of a search as the results sheet shows them (how each criterion is checked, where the facts come from). [REST: GET /api/tasks/{id}/requirements]
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}The account's subscription: plan, status (active, past_due, cancelling, ended), who manages it (admin or lavatop), price and currency, period end, whether it renews, credits and briefs a period. null: no subscription (list_plans, then subscribe). [REST: GET /api/billing/subscription]
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The user's earlier searches whose people can be left out of a new one (exclude_tasks of create_search): all analysed or only the leads. [REST: GET /api/exclusions/sources]
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The people of a search by kind: fit («Подходят»: the leads, in their order), partial («Частично»: some requirement not proven, with what was assumed), miss («Не подходят», with the reason). Compact rows; paginate with offset/limit. get_lead gives one person's dossier with facts. [REST: GET /api/tasks/{id}/leads?kind=]
| Argument | Type | Description |
|---|---|---|
| kind | string | |
| limit | integer | |
| offset | integer | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"kind": {
"enum": [
"fit",
"partial",
"miss"
],
"type": "string",
"default": "fit"
},
"limit": {
"type": "integer",
"default": 25,
"maximum": 100,
"minimum": 1
},
"offset": {
"type": "integer",
"default": 0,
"minimum": 0
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}The user's saved outreach setups across searches (sender, offer, ask, language, accounts, source search), newest used first; new_outreach with preset_id copies one into a fresh generation. [REST: GET /api/outreach/presets]
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| cursor | string |
{
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "integer",
"default": 25,
"maximum": 50,
"minimum": 1
},
"cursor": {
"type": "string",
"maxLength": 200
}
},
"additionalProperties": false
}The tariff catalog: each plan's monthly price (USD, RUB, EUR), credits and briefs a period, and the Enterprise contact. A subscription is bought with subscribe (a LavaTop payment link) or arranged with Catchy (Enterprise). No sign-in needed. [REST: GET /api/plans]
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The user's earlier search onboardings (company, goal, audience), newest first. A new search can start from one of them (get_onboarding_prefill) without the assistants. [REST: GET /api/onboardings]
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The user's searches («Мои поиски»), newest first: id, title, status, leads / partial found, target, credits charged, progress of a running one. [REST: GET /api/tasks]
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| offset | integer | |
| status | string |
{
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "integer",
"default": 25,
"maximum": 100,
"minimum": 1
},
"offset": {
"type": "integer",
"default": 0,
"minimum": 0
},
"status": {
"enum": [
"compiling",
"ready",
"queued",
"running",
"paused",
"asking",
"done",
"stopped",
"failed"
],
"type": "string"
}
},
"additionalProperties": false
}A fresh outreach generation of the search: empty, or with this search's previous setup (reuse_previous) or a saved one (preset_id). Free; the first paid setup step of the generation spends one brief. [REST: POST /api/tasks/{id}/outreach/new]
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| preset_id | string | |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
| reuse_previous | boolean |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"preset_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
},
"reuse_previous": {
"type": "boolean"
}
},
"additionalProperties": false
}«Исключить уже знакомых»: a CSV, TSV, TXT or XLSX file with the people the user already knows (LinkedIn links in any column) -> the profile links found (pass them as exclude_urls of create_search) and the company pages (exclude_company_urls). Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief and may call each assistant once); pass the returned onboarding_id to the next calls and to create_search. [REST: POST /api/assist/exclusions]
| Argument | Type | Description |
|---|---|---|
| file_name* | string | The file's name with its extension. |
| data_base64* | string | The file's bytes, base64. |
| onboarding_id | string | The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search. |
{
"type": "object",
"required": [
"file_name",
"data_base64"
],
"properties": {
"file_name": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "The file's name with its extension."
},
"data_base64": {
"type": "string",
"minLength": 4,
"description": "The file's bytes, base64."
},
"onboarding_id": {
"type": "string",
"pattern": "^[A-Za-z0-9-]{8,64}$",
"description": "The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search."
}
},
"additionalProperties": false
}After a search: the price in credits of finding facts for chosen partial people and moving them to fit («перевести в подходящие», promote=true), or facts only (promote=false). Free, changes nothing; the answer's `credits` is the confirm_credits of start_facts_on_request, `skipped` the people it does not take and why. [REST: POST /api/tasks/{id}/manual/quote]
| Argument | Type | Description |
|---|---|---|
| cids* | array | Person ids (cid) from list_leads. |
| promote | boolean | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id",
"cids"
],
"properties": {
"cids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"maxItems": 300,
"minItems": 1,
"description": "Person ids (cid) from list_leads."
},
"promote": {
"type": "boolean",
"default": true
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}The price in credits of rewriting one message by AI (mode). Free; answers result_id, expected_revision and `credits` for rewrite_message. [REST: POST /api/tasks/{id}/outreach/leads/{cid}/steps/{step_id}/rewrite/quote]
| Argument | Type | Description |
|---|---|---|
| cid* | string | The person's id (cid) from list_leads. |
| mode* | string | other_hook (another fact), shorter, warmer, rewrite (with the note). |
| step_id* | string | The step id of the message (get_outreach_lead steps[].step_id). |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
{
"type": "object",
"required": [
"task_id",
"cid",
"step_id",
"mode"
],
"properties": {
"cid": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The person's id (cid) from list_leads."
},
"mode": {
"enum": [
"other_hook",
"shorter",
"warmer",
"rewrite"
],
"type": "string",
"description": "other_hook (another fact), shorter, warmer, rewrite (with the note)."
},
"step_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The step id of the message (get_outreach_lead steps[].step_id)."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
}
},
"additionalProperties": false
}The price in credits of researching and writing messages for the chosen fit people (per person, total, the most it may hold), the balance, and who is skipped. Free. Its `credits` is the confirm_credits of start_outreach. [REST: POST /api/tasks/{id}/outreach/quote]
| Argument | Type | Description |
|---|---|---|
| cids* | array | Fit people (cid) of the search; get_outreach lists them. |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
{
"type": "object",
"required": [
"task_id",
"cids"
],
"properties": {
"cids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"maxItems": 300,
"minItems": 1,
"description": "Fit people (cid) of the search; get_outreach lists them."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
}
},
"additionalProperties": false
}The price in credits of retrying the people whose messages failed, from where they stopped. Free; its `credits` is the confirm_credits of retry_outreach. [REST: POST /api/tasks/{id}/outreach/retry/quote]
| Argument | Type | Description |
|---|---|---|
| cids | array | The failed people to retry; omitted: every failed person of the generation. |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"cids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"maxItems": 300,
"minItems": 1,
"description": "The failed people to retry; omitted: every failed person of the generation."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
}
},
"additionalProperties": false
}The price in whole credits of running a ready search for `leads` leads (or of continuing a finished one for `leads` more): a low-high range; the start holds the high figure and charges what it really spends. Also the available balance. Show the price to the user and get a yes before run_search / continue_search, passing credits_high as confirm_credits. Free, changes nothing. [REST: GET /api/tasks/{id} (estimate.credits_by_target)]
| Argument | Type | Description |
|---|---|---|
| leads | integer | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"leads": {
"type": "integer",
"default": 20,
"maximum": 100,
"minimum": 1
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}The name a search card shows (1-80 characters). [REST: PUT /api/tasks/{id}/title]
| Argument | Type | Description |
|---|---|---|
| title* | string | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id",
"title"
],
"properties": {
"title": {
"type": "string",
"maxLength": 80,
"minLength": 1
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}Emails a code to reset the password of an account (the answer is the same whether or not the account exists). Then reset_password. [REST: POST /api/auth/password/forgot]
| Argument | Type | Description |
|---|---|---|
| lang | string | The account's language (messages, the texts of its searches). Default en. |
| email* | string |
{
"type": "object",
"required": [
"email"
],
"properties": {
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"description": "The account's language (messages, the texts of its searches). Default en."
},
"email": {
"type": "string",
"maxLength": 254,
"minLength": 3
}
},
"additionalProperties": false
}Sends a new code for a pending registration (at most once a minute; the answer is the same whether or not one is pending). [REST: POST /api/auth/register/resend]
| Argument | Type | Description |
|---|---|---|
| lang | string | The account's language (messages, the texts of its searches). Default en. |
| email* | string |
{
"type": "object",
"required": [
"email"
],
"properties": {
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"description": "The account's language (messages, the texts of its searches). Default en."
},
"email": {
"type": "string",
"maxLength": 254,
"minLength": 3
}
},
"additionalProperties": false
}Sets a new password with the emailed code (every session of the account ends). Then sign_in with it. [REST: POST /api/auth/password/reset]
| Argument | Type | Description |
|---|---|---|
| code* | string | |
| lang | string | The account's language (messages, the texts of its searches). Default en. |
| email* | string | |
| password* | string |
{
"type": "object",
"required": [
"email",
"code",
"password"
],
"properties": {
"code": {
"type": "string",
"maxLength": 20,
"minLength": 4
},
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"description": "The account's language (messages, the texts of its searches). Default en."
},
"email": {
"type": "string",
"maxLength": 254,
"minLength": 3
},
"password": {
"type": "string",
"maxLength": 256,
"minLength": 8
}
},
"additionalProperties": false
}SPENDS CREDITS: quote_outreach_retry first, show the price, after the user's yes pass its `credits` as confirm_credits. [REST: POST /api/tasks/{id}/outreach/retry]
| Argument | Type | Description |
|---|---|---|
| cids | array | The failed people to retry; omitted: every failed person of the generation. |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
| confirm_credits* | integer | The price in credits the matching quote returned, shown to the user and confirmed by them. |
{
"type": "object",
"required": [
"task_id",
"confirm_credits"
],
"properties": {
"cids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"maxItems": 300,
"minItems": 1,
"description": "The failed people to retry; omitted: every failed person of the generation."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
},
"confirm_credits": {
"type": "integer",
"minimum": 0,
"description": "The price in credits the matching quote returned, shown to the user and confirmed by them."
}
},
"additionalProperties": false
}Applies chosen proposals of diagnose_search. SPENDS CREDITS: show the price of that combination and pass it as confirm_credits after the user's yes, with the diagnosis' `version`. For a finished search whose people ran out, `more` (and stop_at_target) say how many more leads to find with the changes. [REST: POST /api/tasks/{id}/revise]
| Argument | Type | Description |
|---|---|---|
| more | integer | |
| accept* | array | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| version | integer | The spec version from get_search (optional: protects against an edit made meanwhile in the web). |
| stop_at_target | boolean | |
| confirm_credits* | integer | The price in credits the matching quote returned, shown to the user and confirmed by them. |
{
"type": "object",
"required": [
"task_id",
"accept",
"confirm_credits"
],
"properties": {
"more": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"accept": {
"type": "array",
"items": {
"type": "string",
"maxLength": 80
},
"maxItems": 10,
"minItems": 1
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"version": {
"type": "integer",
"minimum": 0,
"description": "The spec version from get_search (optional: protects against an edit made meanwhile in the web)."
},
"stop_at_target": {
"type": "boolean"
},
"confirm_credits": {
"type": "integer",
"minimum": 0,
"description": "The price in credits the matching quote returned, shown to the user and confirmed by them."
}
},
"additionalProperties": false
}SPENDS CREDITS: quote_message_rewrite first, show the price, after the user's yes pass its credits, result_id and expected_revision. The new text comes in a few seconds: get_outreach_lead. [REST: POST /api/tasks/{id}/outreach/leads/{cid}/steps/{step_id}/rewrite]
| Argument | Type | Description |
|---|---|---|
| cid* | string | The person's id (cid) from list_leads. |
| mode* | string | other_hook (another fact), shorter, warmer, rewrite (with the note). |
| note | string | |
| step_id* | string | The step id of the message (get_outreach_lead steps[].step_id). |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| result_id | string | |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
| confirm_credits* | integer | The price in credits the matching quote returned, shown to the user and confirmed by them. |
Starts a ready search for `leads` leads. SPENDS CREDITS: first call quote_search, show the price to the user, and only after their explicit yes call this with confirm_credits = the quote's credits_high. stop_at_target (default true) stops at the number of leads. Returns at once (maybe queued); then poll get_search every 30-60 s. Needs a plan or credits on the balance. [REST: POST /api/tasks/{id}/run]
| Argument | Type | Description |
|---|---|---|
| leads* | integer | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| version | integer | The spec version from get_search (optional: protects against an edit made meanwhile in the web). |
| stop_at_target | boolean | |
| confirm_credits* | integer | The price in credits the matching quote returned, shown to the user and confirmed by them. |
{
"type": "object",
"required": [
"task_id",
"leads",
"confirm_credits"
],
"properties": {
"leads": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"version": {
"type": "integer",
"minimum": 0,
"description": "The spec version from get_search (optional: protects against an edit made meanwhile in the web)."
},
"stop_at_target": {
"type": "boolean",
"default": true
},
"confirm_credits": {
"type": "integer",
"minimum": 0,
"description": "The price in credits the matching quote returned, shown to the user and confirmed by them."
}
},
"additionalProperties": false
}«Суть»: offer (what we offer), ask (what we want from the person), optional tone and client_rules, and the message language. [REST: PUT /api/tasks/{id}/outreach/essence]
| Argument | Type | Description |
|---|---|---|
| ask* | string | |
| tone | string | |
| offer* | string | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| language | string | |
| client_rules | string | |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
{
"type": "object",
"required": [
"task_id",
"offer",
"ask"
],
"properties": {
"ask": {
"type": "string",
"maxLength": 3000,
"minLength": 1
},
"tone": {
"type": "string",
"maxLength": 3000
},
"offer": {
"type": "string",
"maxLength": 3000,
"minLength": 1
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"language": {
"enum": [
"english",
"russian",
"spanish",
"french",
"german",
"portuguese",
"italian",
"chinese",
"japanese",
"korean",
"arabic",
"hindi"
],
"type": "string"
},
"client_rules": {
"type": "string",
"maxLength": 3000
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
}
},
"additionalProperties": false
}«Аккаунты»: what the user can write from — email (bool), linkedin (none | basic | sales_navigator), threads (bool), linkedin_comments (public comments on LinkedIn posts, bool). At least one. The route of each person's messages is chosen from these. [REST: PUT /api/tasks/{id}/outreach/funnel]
| Argument | Type | Description |
|---|---|---|
| email* | boolean | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| threads* | boolean | |
| linkedin* | string | |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
| linkedin_comments | boolean |
{
"type": "object",
"required": [
"task_id",
"email",
"linkedin",
"threads"
],
"properties": {
"email": {
"type": "boolean"
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"threads": {
"type": "boolean"
},
"linkedin": {
"enum": [
"none",
"basic",
"sales_navigator"
],
"type": "string"
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
},
"linkedin_comments": {
"type": "boolean"
}
},
"additionalProperties": false
}Who writes the messages: mode=linkedin with the sender's LinkedIn link (the profile and posts are analysed, about a minute), or mode=text with a few sentences about them. The first paid setup step of a generation spends its brief. Then poll get_outreach. [REST: PUT /api/tasks/{id}/outreach/sender]
| Argument | Type | Description |
|---|---|---|
| mode* | string | |
| text | string | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| linkedin_url | string | |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
{
"type": "object",
"required": [
"task_id",
"mode"
],
"properties": {
"mode": {
"enum": [
"linkedin",
"text"
],
"type": "string"
},
"text": {
"type": "string",
"maxLength": 4000,
"minLength": 3
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"linkedin_url": {
"type": "string",
"maxLength": 300
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
}
},
"additionalProperties": false
}Before the run: the search method («способ поиска») — people (search people directly), companies_first (find the companies, then the people in them), via_related_people; only the options get_search detail=spec lists for this spec. The plan and the estimate are made again. [REST: POST /api/tasks/{id}/strategy]
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| version | integer | The spec version from get_search (optional: protects against an edit made meanwhile in the web). |
| strategy* | string |
{
"type": "object",
"required": [
"task_id",
"strategy"
],
"properties": {
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"version": {
"type": "integer",
"minimum": 0,
"description": "The spec version from get_search (optional: protects against an edit made meanwhile in the web)."
},
"strategy": {
"enum": [
"people",
"companies_first",
"via_related_people"
],
"type": "string"
}
},
"additionalProperties": false
}An existing Catchy account: email and password -> an API key for this MCP server (shown once). The web's login limits apply. [REST: POST /api/auth/login]
| Argument | Type | Description |
|---|---|---|
| lang | string | The account's language (messages, the texts of its searches). Default en. |
| email* | string | |
| key_days | integer | null | Lifetime of the key in days; null = no limit. Default 365. |
| key_name | string | Name of the API key in Settings (default «MCP agent»). |
| password* | string | |
| key_access | string |
{
"type": "object",
"required": [
"email",
"password"
],
"properties": {
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"description": "The account's language (messages, the texts of its searches). Default en."
},
"email": {
"type": "string",
"maxLength": 254,
"minLength": 3
},
"key_days": {
"type": [
"integer",
"null"
],
"maximum": 1825,
"minimum": 1,
"description": "Lifetime of the key in days; null = no limit. Default 365."
},
"key_name": {
"type": "string",
"maxLength": 60,
"minLength": 1,
"description": "Name of the API key in Settings (default «MCP agent»)."
},
"password": {
"type": "string",
"maxLength": 256,
"minLength": 1
},
"key_access": {
"enum": [
"full",
"read"
],
"type": "string",
"default": "full"
}
},
"additionalProperties": false
}Registers a new Catchy account and emails a 6-digit code to confirm it (then confirm_sign_up). Set accept_terms=true ONLY after the user has read and agreed to the Terms of Use and the Privacy Policy (their links: catchy_info terms_of_use / privacy_policy) — ask them first. Without a password one is generated and returned once: give it to the user. Returns signup_token for confirm_sign_up. [REST: POST /api/auth/register/start]
| Argument | Type | Description |
|---|---|---|
| lang | string | The account's language (messages, the texts of its searches). Default en. |
| name* | string | |
| email* | string | |
| invite | string | An invite code, when registration is by invitation. |
| password | string | |
| accept_terms* | boolean | The user agreed to the Terms of Use and the Privacy Policy. |
{
"type": "object",
"required": [
"name",
"email",
"accept_terms"
],
"properties": {
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"description": "The account's language (messages, the texts of its searches). Default en."
},
"name": {
"type": "string",
"maxLength": 80,
"minLength": 1
},
"email": {
"type": "string",
"maxLength": 254,
"minLength": 3
},
"invite": {
"type": "string",
"maxLength": 100,
"description": "An invite code, when registration is by invitation."
},
"password": {
"type": "string",
"maxLength": 256,
"minLength": 8
},
"accept_terms": {
"type": "boolean",
"const": true,
"description": "The user agreed to the Terms of Use and the Privacy Policy."
}
},
"additionalProperties": false
}SPENDS CREDITS: quote_facts_on_request first, show the price to the user and after their yes pass its `credits` as confirm_credits. The work runs in the background; poll get_search / list_leads. [REST: POST /api/tasks/{id}/manual]
| Argument | Type | Description |
|---|---|---|
| cids* | array | Person ids (cid) from list_leads. |
| promote | boolean | |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| confirm_credits* | integer | The price in credits the matching quote returned, shown to the user and confirmed by them. |
{
"type": "object",
"required": [
"task_id",
"cids",
"confirm_credits"
],
"properties": {
"cids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"maxItems": 300,
"minItems": 1,
"description": "Person ids (cid) from list_leads."
},
"promote": {
"type": "boolean",
"default": true
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"confirm_credits": {
"type": "integer",
"minimum": 0,
"description": "The price in credits the matching quote returned, shown to the user and confirmed by them."
}
},
"additionalProperties": false
}SPENDS CREDITS: quote_outreach first, show the price to the user and after their yes pass its `credits` as confirm_credits. Needs the sender ready, the essence and the accounts. Runs in the background (minutes); poll get_outreach every 30-60 s. [REST: POST /api/tasks/{id}/outreach/start]
| Argument | Type | Description |
|---|---|---|
| cids* | array | Fit people (cid) of the search; get_outreach lists them. |
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
| generation_id | string | The outreach generation id (get_outreach campaign.generation.id); omitted: the current one. |
| confirm_credits* | integer | The price in credits the matching quote returned, shown to the user and confirmed by them. |
{
"type": "object",
"required": [
"task_id",
"cids",
"confirm_credits"
],
"properties": {
"cids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"maxItems": 300,
"minItems": 1,
"description": "Fit people (cid) of the search; get_outreach lists them."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
},
"confirm_credits": {
"type": "integer",
"minimum": 0,
"description": "The price in credits the matching quote returned, shown to the user and confirmed by them."
}
},
"additionalProperties": false
}Creates a LavaTop payment for a monthly plan (start, growth, scale; prices in list_plans) and returns its payment_url and order id. Confirm the plan, price and currency with the user first. GIVE THE LINK TO THE USER: a person pays on LavaTop's page by card, SBP or PayPal (an agent cannot). Currency is also the method: RUB — Russian cards and SBP; USD — foreign cards, PayPal, Apple Pay (Russian cards pay only in RUB); EUR is not available. A USD link lives 15 minutes, a RUB link 24 hours. Then poll get_payment_status every 15-30 s until paid; the plan's credits and briefs arrive with the payment and renew monthly until cancel_subscription. [REST: POST /api/billing/checkout]
| Argument | Type | Description |
|---|---|---|
| plan* | string | |
| currency | string |
{
"type": "object",
"required": [
"plan"
],
"properties": {
"plan": {
"enum": [
"start",
"growth",
"scale"
],
"type": "string"
},
"currency": {
"enum": [
"USD",
"RUB"
],
"type": "string",
"default": "USD"
}
},
"additionalProperties": false
}Step 3 («Кому пишем»): three customer profiles (ICP) to search for, from the company and the goal; each with a short title, the profile text and why. The chosen text is the `icp` of create_search. Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief and may call each assistant once); pass the returned onboarding_id to the next calls and to create_search. [REST: POST /api/assist/audiences]
| Argument | Type | Description |
|---|---|---|
| goal* | string | |
| company* | string | |
| onboarding_id | string | The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search. |
{
"type": "object",
"required": [
"company",
"goal"
],
"properties": {
"goal": {
"type": "string",
"maxLength": 2000,
"minLength": 1
},
"company": {
"type": "string",
"maxLength": 5000,
"minLength": 1
},
"onboarding_id": {
"type": "string",
"pattern": "^[A-Za-z0-9-]{8,64}$",
"description": "The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search."
}
},
"additionalProperties": false
}Step 1 of a new search («Компания»): reads the user's company site (url) or a text about it and writes a short plain-language description of what it sells, to whom and why it matters. The user may edit it before create_search. Takes up to a minute. Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief and may call each assistant once); pass the returned onboarding_id to the next calls and to create_search. [REST: POST /api/assist/company]
| Argument | Type | Description |
|---|---|---|
| url | string | The company's site, e.g. acme.com. |
| text | string | Or: a text about the company. |
| onboarding_id | string | The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search. |
{
"type": "object",
"required": [],
"properties": {
"url": {
"type": "string",
"maxLength": 500,
"description": "The company's site, e.g. acme.com."
},
"text": {
"type": "string",
"maxLength": 20000,
"description": "Or: a text about the company."
},
"onboarding_id": {
"type": "string",
"pattern": "^[A-Za-z0-9-]{8,64}$",
"description": "The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search."
}
},
"additionalProperties": false
}Step 2 («Цель»): four goals for the outreach to the people found (e.g. invite to a call), from the company description. The user picks or writes one. Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief and may call each assistant once); pass the returned onboarding_id to the next calls and to create_search. [REST: POST /api/assist/goals]
| Argument | Type | Description |
|---|---|---|
| company* | string | The company description (step 1). |
| onboarding_id | string | The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search. |
{
"type": "object",
"required": [
"company"
],
"properties": {
"company": {
"type": "string",
"maxLength": 5000,
"minLength": 1,
"description": "The company description (step 1)."
},
"onboarding_id": {
"type": "string",
"pattern": "^[A-Za-z0-9-]{8,64}$",
"description": "The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search."
}
},
"additionalProperties": false
}A draft of «Что предлагаем» (the offer) from the search's onboarding. Free for the user (it may spend the generation's brief). [REST: POST /api/tasks/{id}/outreach/essence/suggest]
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The search id (task id), e.g. from list_searches or create_search. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 17, 2026.
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.
| onboarding_id | string | The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search. |
| exclude_companies | boolean | Also leave out the companies of those people. |
| exclude_company_urls | array |
{
"type": "object",
"required": [
"company",
"icp"
],
"properties": {
"icp": {
"type": "string",
"maxLength": 5000,
"minLength": 1,
"description": "Whom to find: the customer profile (step 3)."
},
"goal": {
"type": "string",
"maxLength": 2000,
"description": "What the outreach should achieve (step 2)."
},
"company": {
"type": "string",
"maxLength": 5000,
"minLength": 1,
"description": "What the user's company does (step 1)."
},
"language": {
"enum": [
"english",
"russian"
],
"type": "string",
"description": "Language of the outreach messages (default english)."
},
"source_task": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The earlier onboarding this one was filled from (get_onboarding_prefill)."
},
"exclude_urls": {
"type": "array",
"items": {
"type": "string",
"maxLength": 300
},
"maxItems": 50000,
"description": "LinkedIn profile links of people to leave out."
},
"exclude_scope": {
"enum": [
"all",
"leads"
],
"type": "string",
"description": "From those searches: everyone analysed (all) or only leads."
},
"exclude_tasks": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$"
},
"maxItems": 50,
"description": "Earlier searches whose people to leave out."
},
"onboarding_id": {
"type": "string",
"pattern": "^[A-Za-z0-9-]{8,64}$",
"description": "The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search."
},
"exclude_companies": {
"type": "boolean",
"description": "Also leave out the companies of those people."
},
"exclude_company_urls": {
"type": "array",
"items": {
"type": "string",
"maxLength": 300
},
"maxItems": 5000
}
},
"additionalProperties": false
}| expected_revision |
| integer |
{
"type": "object",
"required": [
"task_id",
"cid",
"step_id",
"mode",
"confirm_credits"
],
"properties": {
"cid": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The person's id (cid) from list_leads."
},
"mode": {
"enum": [
"other_hook",
"shorter",
"warmer",
"rewrite"
],
"type": "string",
"description": "other_hook (another fact), shorter, warmer, rewrite (with the note)."
},
"note": {
"type": "string",
"maxLength": 500
},
"step_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The step id of the message (get_outreach_lead steps[].step_id)."
},
"task_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The search id (task id), e.g. from list_searches or create_search."
},
"result_id": {
"type": "string",
"maxLength": 80
},
"generation_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_\\-]{1,80}$",
"description": "The outreach generation id (get_outreach campaign.generation.id); omitted: the current one."
},
"confirm_credits": {
"type": "integer",
"minimum": 0,
"description": "The price in credits the matching quote returned, shown to the user and confirmed by them."
},
"expected_revision": {
"type": "integer",
"minimum": 0
}
},
"additionalProperties": false
}