Connect AI clients to your Dactic work context through a hosted MCP service.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
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.
Answer a question from your own Dactic context: matches holds evidence from your synced work data and current department policies related to the question; your_profile holds your work context, skills, agents and connected apps. When nothing matches, say so; never another user's data, even for org admins.
Monday board id or board name. Limits evidence to that Monday board and drops other Monday boards plus Chat, Gmail, and any other non-Monday evidence. Only boards the caller has approved are accepted.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http dactic-mcp https://mcp.app.dactic.io/mcp
Answer a question from your own Dactic context: matches holds evidence from your synced work data and current department policies related to the question; your_profile holds your work context, skills, agents and connected apps. When nothing matches, say so; never another user's data, even for org admins.
| Argument | Type | Description |
|---|---|---|
| board | string | Monday board id or board name. Limits evidence to that Monday board and drops other Monday boards plus Chat, Gmail, and any other non-Monday evidence. Only boards the caller has approved are accepted. |
| limit | integer | |
| question* | string | |
| source_type | string |
{
"type": "object",
"required": [
"question"
],
"properties": {
"board": {
"type": "string",
"description": "Monday board id or board name. Limits evidence to that Monday board and drops other Monday boards plus Chat, Gmail, and any other non-Monday evidence. Only boards the caller has approved are accepted."
},
"limit": {
"type": "integer"
},
"question": {
"type": "string"
},
"source_type": {
"type": "string"
}
},
"additionalProperties": false
}Advisory check of a draft reply, plan or action against your department's Dactic policies. Returns findings that quote the policy and the draft verbatim, with a suggested change, and says how many policies were checked. Present the result as advice: it is never a compliance sign-off. not_assessed means the check couldn't run; the applicable policies are listed instead.
| Argument | Type | Description |
|---|---|---|
| kind | string | |
| draft* | string | |
| context | string | |
| categories | array |
{
"type": "object",
"required": [
"draft"
],
"properties": {
"kind": {
"enum": [
"reply",
"plan",
"action"
],
"type": "string"
},
"draft": {
"type": "string",
"maxLength": 8000
},
"context": {
"type": "string",
"maxLength": 1000
},
"categories": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
}Is my Dactic knowledge up to date? Reports each surface (app sync, confirmed knowledge, terminology, approved playbook, department policies, skills, and optionally one agent) as fresh, stale, empty or unknown, with a recommendation for anything not fresh. Pass refs from other Dactic tools to check specific items. scope=org is for org admins.
| Argument | Type | Description |
|---|---|---|
| refs | array | |
| scope | string | |
| agent_id | string |
{
"type": "object",
"properties": {
"refs": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 50
},
"scope": {
"enum": [
"me",
"org"
],
"type": "string"
},
"agent_id": {
"type": "string"
}
},
"additionalProperties": false
}Compare two stored artifact versions of the same accessible agent/platform, with instruction diffs and skill additions/removals. Missing guardrails/parameters remain unknown. Never rolls back or deploys.
| Argument | Type | Description |
|---|---|---|
| agent_id* | string | |
| platform | string | |
| to_version* | integer | |
| from_version* | integer |
{
"type": "object",
"required": [
"agent_id",
"from_version",
"to_version"
],
"properties": {
"agent_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"platform": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"to_version": {
"type": "integer",
"minimum": 1
},
"from_version": {
"type": "integer",
"minimum": 1
}
},
"additionalProperties": false
}Draft a new Dactic agent, and the new skills it needs, from a process the user describes in this chat — use this when the user's existing skills don't cover the work (synthesize_agent only reuses existing skills). Before calling, ask the user for the purpose, the concrete steps in order, when it should run, the data sources or tools it uses and anything it must never do; then confirm the summary with them. Runs in the background: returns a task_id; call get_task_status until succeeded (with the draft and its review link) or failed. The draft is saved for review in the Dactic app and is never deployed from here. target_platform claude only; Monday agents are created in the Dactic app.
| Argument | Type | Description |
|---|---|---|
| name | string | |
| notes | string | |
| steps* | array | |
| purpose* | string | |
| trigger | string | |
| resources | array | |
| constraints | array | |
| idempotency_key | string | |
| target_platform |
First deployment of your selected saved draft. Call without confirmation_code for a preview, show it to the user and obtain authorization, then repeat the same definition/target with the code. Checks skills, source approvals and existing deploy readiness/billing gates. Returns a background task; poll get_task_status for deployment state. An existing deployment is identified without redeploying.
| Argument | Type | Description |
|---|---|---|
| definition_id* | string | |
| target_workspace* | string | |
| confirmation_code | string |
{
"type": "object",
"required": [
"definition_id",
"target_workspace"
],
"properties": {
"definition_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"target_workspace": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"confirmation_code": {
"type": "string",
"maxLength": 100,
"minLength": 1
}
},
"additionalProperties": false
}Fetch the full text of one Dactic item by the id search returned, with a link to it.
| Argument | Type | Description |
|---|---|---|
| id* | string |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string"
}
},
"additionalProperties": false
}Assess task preparation using available knowledge, skills, policies, terminology and sync readiness. Returns blocking/nonblocking gaps; unknown requirements or execution permissions remain unknown.
| Argument | Type | Description |
|---|---|---|
| task* | string | |
| agent_id | string | |
| required_inputs | array | |
| available_inputs | array |
{
"type": "object",
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"maxLength": 4000,
"minLength": 1
},
"agent_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"required_inputs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 30
},
"available_inputs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 30
}
},
"additionalProperties": false
}Get one of your Dactic agents by id: its name, platform, status, complete instructions and every skill (name, description, full procedure). Never returns another user's agent.
| Argument | Type | Description |
|---|---|---|
| enrich | boolean | |
| agent_id* | string |
{
"type": "object",
"required": [
"agent_id"
],
"properties": {
"enrich": {
"type": "boolean"
},
"agent_id": {
"type": "string"
}
},
"additionalProperties": false
}Get everything a task needs from Dactic in one call; use it before doing a task, especially when running an agent. With agent_id: that agent's complete instructions and skills. Without: your most relevant skills. Plus your confirmed knowledge and related evidence, your department's applicable policies with citations, confirmed meanings of company terms (unresolved terms are listed, never guessed) and a freshness summary. Fits token_budget by dropping whole lower-priority items, listed in omitted.
| Argument | Type | Description |
|---|---|---|
| task* | string | |
| include | array | |
| agent_id | string | |
| token_budget | integer |
{
"type": "object",
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"maxLength": 2000
},
"include": {
"type": "array",
"items": {
"enum": [
"skills",
"knowledge",
"policy",
"terms",
"freshness"
],
"type": "string"
}
},
"agent_id": {
"type": "string"
},
"token_budget": {
"type": "integer",
"maximum": 16000,
"minimum": 1000
}
},
"additionalProperties": false
}Retrieve added/updated/removed permitted knowledge and published policies since an actor-bound snapshot cursor. Omit cursor for a complete bounded baseline. Expired cursors or changed scopes/permissions require a fresh baseline. Returns snapshot differences, not every intermediate change event; the host retains the cursor.
| Argument | Type | Description |
|---|---|---|
| cursor | string | |
| include | array |
{
"type": "object",
"required": [],
"properties": {
"cursor": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"include": {
"type": "array",
"items": {
"enum": [
"knowledge",
"policies"
],
"type": "string"
},
"maxItems": 2,
"minItems": 1
}
},
"additionalProperties": false
}Follow bounded explicit stored links from an approved board, accessible agent/project or confirmed term. Returns entities, relationship bases, citations and missing-link gaps. Text similarity never establishes a dependency.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| entity_id* | string | |
| entity_type* | string |
{
"type": "object",
"required": [
"entity_type",
"entity_id"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"entity_id": {
"type": "string",
"maxLength": 255,
"minLength": 1
},
"entity_type": {
"enum": [
"board",
"agent",
"project",
"term"
],
"type": "string"
}
},
"additionalProperties": false
}Follow the recorded processing/application state of your submitted agent feedback. No immediate agent change is implied.
| Argument | Type | Description |
|---|---|---|
| feedback_id* | string |
{
"type": "object",
"required": [
"feedback_id"
],
"properties": {
"feedback_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
}
},
"additionalProperties": false
}Where did that come from? For refs returned by other Dactic tools (1-20), describes each item's source and a confidence of high, medium or low from a fixed rubric, with the rule that applied in `basis`. Rubric — terminology: high when confirmed with score >= 0.9 and no conflict, medium when confirmed otherwise, low when not confirmed. Knowledge: high when confirmed in an interview, medium when inferred from 3+ evidence items (or confirmed without a recorded confirmation), low otherwise or when disputed. Evidence: high when it supports confirmed knowledge, medium when it supports unconfirmed knowledge, low otherwise. Policy: high when in the current published COE version, medium when ingested from a document but not published, low with no source document. Skill: high when the owner has an approved playbook and a live agent uses it, medium when active, low when retired. Playbook: high approved, medium needs follow-up, low otherwise. Never repeats evidence text.
| Argument | Type | Description |
|---|---|---|
| refs* | array |
{
"type": "object",
"required": [
"refs"
],
"properties": {
"refs": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 20,
"minItems": 1
}
},
"additionalProperties": false
}Get your department's current policies with their source document. With query: the policies that apply to it (all of them when your department has few, else the closest matches; coverage says which). Returns not_found when none are published.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | |
| category | string | |
| policy_id | string |
{
"type": "object",
"properties": {
"limit": {
"type": "integer"
},
"query": {
"type": "string"
},
"category": {
"type": "string"
},
"policy_id": {
"type": "string"
}
},
"additionalProperties": false
}Get one of your Dactic skills by id, with its full procedure at disclosure_tier L3.
| Argument | Type | Description |
|---|---|---|
| skill_id* | string | |
| disclosure_tier | string |
{
"type": "object",
"required": [
"skill_id"
],
"properties": {
"skill_id": {
"type": "string"
},
"disclosure_tier": {
"enum": [
"L1",
"L2",
"L3"
],
"type": "string"
}
},
"additionalProperties": false
}How often your Dactic skills were listed and loaded by AI clients (ChatGPT, Claude…) over the last 7, 30 or 90 days, how many live agents use each, and a suggestion (promote, keep, review or trim) with its basis. Suggestions are advice and never change anything. data_since is when counting started; there is no earlier history. scope=org is for org admins.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| scope | string | |
| skill_slug | string | |
| next_cursor | string | |
| window_days | integer |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"scope": {
"enum": [
"me",
"org"
],
"type": "string"
},
"skill_slug": {
"type": "string",
"maxLength": 128
},
"next_cursor": {
"type": "string"
},
"window_days": {
"enum": [
7,
30,
90
],
"type": "integer"
}
},
"additionalProperties": false
}Report recorded sync progress, last successful sync, approved source coverage and safe recovery guidance. Credential linkage is not proof of current access.
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}Status of a background task you started (e.g. synthesize_agent): queued, running, succeeded (with its result) or failed (with error_message). Only your own tasks; anything else is not_found.
| Argument | Type | Description |
|---|---|---|
| task_id* | string |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"maxLength": 64
}
},
"additionalProperties": false
}Your Dactic AI usage (tokens by operation) over the last N days; scope=org is for org admins.
| Argument | Type | Description |
|---|---|---|
| days | integer | |
| scope | string |
{
"type": "object",
"properties": {
"days": {
"type": "integer"
},
"scope": {
"enum": [
"self",
"org"
],
"type": "string"
}
},
"additionalProperties": false
}Your own Dactic profile for personalising answers: job title, team, department and role; work context (role, guardrails, preferences); confirmed knowledge (paginated; unconfirmed files are counted, not shown); connected apps; tools you use. Only ever your own data, even for org admins.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| cursor | string | |
| sections | array |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1
},
"cursor": {
"type": "string"
},
"sections": {
"type": "array",
"items": {
"enum": [
"profile",
"work_context",
"knowledge",
"connections",
"preferences"
],
"type": "string"
}
}
},
"additionalProperties": false
}Build advisory human-reviewed workflow options using accessible agents, context gaps, connection/sync readiness and provisional platform capabilities. Separates source, execution-platform and host connectors. Returns next actions and conservative net human-hours estimates only from user-confirmed measurements. Missing measurements trigger a question. Never executes, connects, schedules or deploys.
| Argument | Type | Description |
|---|---|---|
| goal* | string | |
| agent_id | string | |
| where_stuck | string | |
| manual_steps | array | |
| measurements | object | |
| required_inputs | array | |
| target_platform | string | |
| available_inputs | array |
{
"type": "object",
"required": [
"goal"
],
"properties": {
"goal": {
"type": "string",
"maxLength": 4000,
"minLength": 1
},
"agent_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"where_stuck": {
"type": "string",
"maxLength": 4000,
"minLength": 1
},
"manual_steps": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 30
},
"measurements": {
"type": "object",
"properties": {
"confirmed": {
"type": "boolean"
},
"setup_hours": {
"type": "number",
"minimum": 0
},
"pilot_observed": {
"type": "boolean"
},
"completion_rate": {
"type": "number",
"maximum": 1,
"minimum": 0
},
"tasks_per_period": {
"type": "number",
"minimum": 0
},
"eligible_coverage": {
"type": "number",
"maximum": 1,
"minimum": 0
},
"maintenance_hours": {
"type": "number",
"minimum": 0
},
"failed_attempt_hours": {
"type": "number",
"minimum": 0
},
"manual_hours_per_task": {
"type": "number",
"minimum": 0
},
"remaining_human_hours_per_task": {
"type": "array",
"items": {
"type": "number",
"minimum": 0
},
"maxItems": 2,
"minItems": 2
}
},
"additionalProperties": false
},
"required_inputs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 30
},
"target_platform": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"available_inputs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 30
}
},
"additionalProperties": false
}Run one of your deployed Dactic agents. Claude agents start a Managed Agent session; Monday agents are run by Monday's own board automation. The response always includes the agent's complete instructions and skills. Retrying the same request returns the same run instead of starting another.
| Argument | Type | Description |
|---|---|---|
| input | object | |
| agent_id* | string | |
| idempotency_key | string | |
| include_context | boolean |
{
"type": "object",
"required": [
"agent_id"
],
"properties": {
"input": {
"type": "object"
},
"agent_id": {
"type": "string"
},
"idempotency_key": {
"type": "string",
"maxLength": 128
},
"include_context": {
"type": "boolean"
}
},
"additionalProperties": false
}List the Dactic agents you (the signed-in user) have deployed, newest first. Returns each agent's id, name, platform and status. Use load_agent to run one or get_agent for its details. Returns not_found when you have none.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| cursor | string | |
| enrich | boolean | |
| target | string |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"cursor": {
"type": "string"
},
"enrich": {
"type": "boolean"
},
"target": {
"enum": [
"monday",
"claude",
"all"
],
"type": "string"
}
},
"additionalProperties": false
}List your active Dactic skills (procedures derived from your interviews). disclosure_tier L1 returns a catalog; L2/L3 add the procedure. Use get_skill for one skill. Returns not_found when you have none.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | |
| approved_only | boolean | |
| disclosure_tier | string |
{
"type": "object",
"properties": {
"limit": {
"type": "integer"
},
"query": {
"type": "string"
},
"approved_only": {
"type": "boolean"
},
"disclosure_tier": {
"enum": [
"L1",
"L2",
"L3"
],
"type": "string"
}
},
"additionalProperties": false
}Load one of your Dactic agents (by agent_id or exact agent_name) so you can run it in this chat: returns its complete instructions and skills. Follow them exactly. Returns not_ready when the agent has no approved instructions, and not_found when no agent matches; it never returns a partial agent.
| Argument | Type | Description |
|---|---|---|
| agent_id | string | |
| agent_name | string |
{
"type": "object",
"properties": {
"agent_id": {
"type": "string"
},
"agent_name": {
"type": "string",
"maxLength": 200
}
},
"additionalProperties": false
}Query the approved synced Monday item view with supported scalar filters, sorting, grouping and count/sum aggregation. Fields are base identifiers or column:<stored-column-id>. Returns typed rows, pagination and explicit sync/coverage limits. Older syncs may lack structured columns. Never accepts SQL.
| Argument | Type | Description |
|---|---|---|
| sort | array | |
| view | string | |
| limit | integer | |
| cursor | string | |
| fields | array | |
| filters | array | |
| board_id | string | |
| group_by | array | |
| aggregate | any |
{
"type": "object",
"required": [],
"properties": {
"sort": {
"type": "array",
"items": {
"type": "object",
"required": [
"field"
],
"properties": {
"field": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"direction": {
"enum": [
"asc",
"desc"
],
"type": "string"
}
},
"additionalProperties": false
},
"maxItems": 3
},
"view": {
"enum": [
"monday_items"
],
"type": "string"
},
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"cursor": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"fields": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 20,
"minItems": 1
},
"filters": {
"type": "array",
"items": {
"type": "object",
"required": [
"field",
"op",
"value"
],
"properties": {
"op": {
"enum": [
"eq",
"ne",
"gt",
"gte",
"lt",
"lte",
"contains"
],
"type": "string"
},
"field": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"value": {
"type": [
"string",
"number",
"boolean",
"null"
]
}
},
"additionalProperties": false
},
"maxItems": 10
},
"board_id": {
"type": "string",
"maxLength": 128,
"minLength": 1
},
"group_by": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 3
},
"aggregate": {
"oneOf": [
{
"enum": [
"count"
],
"type": "string"
},
{
"type": "object",
"required": [
"op",
"field"
],
"properties": {
"op": {
"enum": [
"sum"
],
"type": "string"
},
"field": {
"type": "string",
"maxLength": 200,
"minLength": 1
}
},
"additionalProperties": false
}
]
}
},
"additionalProperties": false
}Match a task to accessible deployed agents by their stored instructions and skills. Returns candidate evidence and limitations; never runs or creates an agent.
| Argument | Type | Description |
|---|---|---|
| task* | string | |
| limit | integer |
{
"type": "object",
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"maxLength": 4000,
"minLength": 1
},
"limit": {
"type": "integer",
"maximum": 10,
"minimum": 1
}
},
"additionalProperties": false
}After confirming the user's goal, save a new recommendation iteration containing validated Claude draft proposals from their own skills/context. Optional priorities produce up to three proposals. A proposal never copies an agent or draft the user already has: when their skills are all in use the result is existing_agent_covers with those agents. Returns a background task; poll get_task_status. Monday synthesis is unavailable in this path. Never deploys.
| Argument | Type | Description |
|---|---|---|
| goal* | string | |
| priorities | array | |
| idempotency_key | string | |
| target_platform | string | |
| previous_iteration_id | string |
{
"type": "object",
"required": [
"goal"
],
"properties": {
"goal": {
"type": "string",
"maxLength": 4000,
"minLength": 1
},
"priorities": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500,
"minLength": 1
},
"maxItems": 3
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"minLength": 1
},
"target_platform": {
"enum": [
"claude"
],
"type": "string"
},
"previous_iteration_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
}
},
"additionalProperties": false
}Look up what company-specific terms mean, from your organization's confirmed Dactic terminology only. Terms that aren't confirmed come back in gaps; never guess their meaning.
| Argument | Type | Description |
|---|---|---|
| team | string | |
| terms* | array |
{
"type": "object",
"required": [
"terms"
],
"properties": {
"team": {
"type": "string"
},
"terms": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
}Find comparable recent runs or resolved feedback owned by you. Returns recorded summaries/outcomes, citations and uncertainty; missing actions/outcomes remain unknown. Past outcomes do not guarantee success.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| situation* | string |
{
"type": "object",
"required": [
"situation"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1
},
"situation": {
"type": "string",
"maxLength": 4000,
"minLength": 1
}
},
"additionalProperties": false
}Search your Dactic knowledge (your skills, agents and approved playbooks, and your organization's confirmed terminology, plus current department policies). Returns results with an id, title and link; call fetch with an id for the full text.
| Argument | Type | Description |
|---|---|---|
| query* | string |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string"
}
},
"additionalProperties": false
}File feedback about one of your own Dactic agents (e.g. 'it keeps CC'ing finance'). Quote the user's words in detail. First call without confirmation_code: you get a preview and a confirmation_code and nothing is saved; show the preview, ask the user to confirm, then call again with the same fields plus confirmation_code. It's applied at the agent's next refresh, not immediately. Only for your own agents.
| Argument | Type | Description |
|---|---|---|
| agent* | object | |
| detail | string | |
| target | object | |
| summary* | string | |
| category | string | |
| severity | string | |
| idempotency_key | string | |
| confirmation_code | string | |
| expected_behavior | string |
{
"type": "object",
"required": [
"agent",
"summary"
],
"properties": {
"agent": {
"type": "object",
"properties": {
"agent_id": {
"type": "string"
},
"agent_name": {
"type": "string",
"maxLength": 200
}
},
"additionalProperties": false
},
"detail": {
"type": "string",
"maxLength": 8000
},
"target": {
"type": "object",
"properties": {
"type": {
"enum": [
"skill",
"instruction_section",
"context",
"unknown"
],
"type": "string"
},
"section": {
"enum": [
"Role",
"Objective",
"Operating Procedure",
"Decision Rules",
"Communication",
"Guardrails",
"Escalation",
"Dynamic Parameters",
"Termination"
],
"type": "string"
},
"skill_slug": {
"type": "string"
}
},
"additionalProperties": false
},
"summary": {
"type": "string",
"maxLength": 500
},
"category": {
"enum": [
"accuracy",
"tone",
"missed_context",
"wrong_output",
"other"
],
"type": "string"
},
"severity": {
"enum": [
"low",
"medium",
"high"
],
"type": "string"
},
"idempotency_key": {
"type": "string",
"maxLength": 128
},
"confirmation_code": {
"type": "string"
},
"expected_behavior": {
"type": "string",
"maxLength": 2000
}
},
"additionalProperties": false
}Draft a new Dactic agent for a task the user describes, built only from the user's own Dactic skills, policies and work context. Runs in the background: it returns a task_id at once; call get_task_status with it until the status is succeeded or failed. The result is a draft saved for review in the Dactic app — it is never deployed from here. If none of the user's skills fit, the result says not_enough_material: then offer create_agent_from_process, which builds the agent and its new skills from the process the user describes. If the user's existing agents or drafts already use every skill that fits, the result says existing_agent_covers and names them instead of drafting a duplicate; for a genuinely new process use create_agent_from_process. Confirm the task with the user before calling. target_platform claude only for now.
| Argument | Type | Description |
|---|---|---|
| name | string | |
| idempotency_key | string | |
| target_platform | string | |
| task_description* | string |
{
"type": "object",
"required": [
"task_description"
],
"properties": {
"name": {
"type": "string",
"maxLength": 80
},
"idempotency_key": {
"type": "string",
"maxLength": 128
},
"target_platform": {
"enum": [
"claude",
"openai",
"monday"
],
"type": "string"
},
"task_description": {
"type": "string",
"maxLength": 4000
}
},
"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 4, 2026.
| string |
{
"type": "object",
"required": [
"purpose",
"steps"
],
"properties": {
"name": {
"type": "string",
"maxLength": 80
},
"notes": {
"type": "string",
"maxLength": 2000
},
"steps": {
"type": "array",
"items": {
"type": "string",
"maxLength": 2000
},
"maxItems": 20,
"minItems": 1
},
"purpose": {
"type": "string",
"maxLength": 2000
},
"trigger": {
"type": "string",
"maxLength": 2000
},
"resources": {
"type": "array",
"items": {
"type": "string",
"maxLength": 2000
},
"maxItems": 20
},
"constraints": {
"type": "array",
"items": {
"type": "string",
"maxLength": 2000
},
"maxItems": 20
},
"idempotency_key": {
"type": "string",
"maxLength": 128
},
"target_platform": {
"enum": [
"claude",
"monday"
],
"type": "string"
}
},
"additionalProperties": false
}