Read the Google Discover feed of a country and check if your domain is in it.
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.
Whether cards from a domain are in a country's Discover feed now, and at which positions. Reads the same feed as get_discover_feed (signed out, from a home IP in the country) and keeps the cards whose link is on the domain or one of its subdomains. in_feed is false when none is there right now; feed_size says how many cards the feed held. Run it on a schedule to see when a story enters and leaves.
The site's domain, e.g. example-news.com. Its subdomains count too.
Country of the feed, ISO 3166-1 alpha-2 (US, GB, DE, PL ...). The feed is read from a home IP there, so its stories are the ones Discover shows in that country. Default: US.
Language of the feed, BCP 47 (en-US, de-DE, pt-BR). Default: the country's main language.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http google-discover https://cotlet.dev/mcp/v1/google-discover/connect
Whether cards from a domain are in a country's Discover feed now, and at which positions. Reads the same feed as get_discover_feed (signed out, from a home IP in the country) and keeps the cards whose link is on the domain or one of its subdomains. in_feed is false when none is there right now; feed_size says how many cards the feed held. Run it on a schedule to see when a story enters and leaves.
| Argument | Type | Description |
|---|---|---|
| domain* | string | The site's domain, e.g. example-news.com. Its subdomains count too. |
| country | string | Country of the feed, ISO 3166-1 alpha-2 (US, GB, DE, PL ...). The feed is read from a home IP there, so its stories are the ones Discover shows in that country. Default: US. |
| language | string | Language of the feed, BCP 47 (en-US, de-DE, pt-BR). Default: the country's main language. |
{
"type": "object",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"maxLength": 253,
"minLength": 3,
"description": "The site's domain, e.g. example-news.com. Its subdomains count too."
},
"country": {
"type": "string",
"pattern": "^[A-Za-z]{2}$",
"description": "Country of the feed, ISO 3166-1 alpha-2 (US, GB, DE, PL ...). The feed is read from a home IP there, so its stories are the ones Discover shows in that country. Default: US."
},
"language": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[A-Za-z]{2,4})?$",
"description": "Language of the feed, BCP 47 (en-US, de-DE, pt-BR). Default: the country's main language."
}
},
"additionalProperties": false
}Up to 300 different cards Discover shows in a country, from many reads, with how often each appeared. One read of the Discover feed holds about 31 cards, and each read draws them from a larger pool. This tool reads the feed of the country many times in parallel, each time from another home IP there, until it has the number of different cards asked for or the pool runs dry, and returns them at once. seen_in says in how many reads a card appeared (a card in most reads is the core of the feed, one seen once is rare) and best_position its highest place. Cards come most often seen first. complete is false when the feed held fewer different cards than asked for in the time of one call. A call takes up to about 70 seconds and costs more credits than one read, because it makes many.
| Argument | Type | Description |
|---|---|---|
| cards | integer | How many different cards to collect, at most 300. Default: 300. |
| country | string | Country of the feed, ISO 3166-1 alpha-2 (US, GB, DE, PL ...). The feed is read from a home IP there, so its stories are the ones Discover shows in that country. Default: US. |
| language | string | Language of the feed, BCP 47 (en-US, de-DE, pt-BR). Default: the country's main language. |
{
"type": "object",
"required": [],
"properties": {
"cards": {
"type": "integer",
"maximum": 300,
"minimum": 1,
"description": "How many different cards to collect, at most 300. Default: 300."
},
"country": {
"type": "string",
"pattern": "^[A-Za-z]{2}$",
"description": "Country of the feed, ISO 3166-1 alpha-2 (US, GB, DE, PL ...). The feed is read from a home IP there, so its stories are the ones Discover shows in that country. Default: US."
},
"language": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[A-Za-z]{2,4})?$",
"description": "Language of the feed, BCP 47 (en-US, de-DE, pt-BR). Default: the country's main language."
}
},
"additionalProperties": false
}How to work in an app by clicking in the user's Cloud Browser with Cotlet's browser tools: which browser to use for this workspace and the sign-in link, the method step by step, the app's screens, menus and actions, notes, and the app's dedicated tools when Cotlet has them. Call it before the first browser step in an app. Works for any web app; one outside Cotlet's catalog gets the general method. Free, no browser session.
| Argument | Type | Description |
|---|---|---|
| app | string | The app's name or Cotlet slug. Default: Google Discover. |
| task | string | What the user wants done in the app, in their words. |
{
"type": "object",
"properties": {
"app": {
"type": "string",
"maxLength": 120,
"description": "The app's name or Cotlet slug. Default: Google Discover."
},
"task": {
"type": "string",
"maxLength": 500,
"description": "What the user wants done in the app, in their words."
}
},
"additionalProperties": false
}The apps of the user's workspace and whether each works now: the app account in the user's Cloud Browser (connected, signed out, signed in but not connected), and the one step the user has to take, with the console link. Free. Needs the user's Cotlet API key or sign-in.
| Argument | Type | Description |
|---|---|---|
| app | string | Only this app, e.g. skool. |
{
"type": "object",
"properties": {
"app": {
"type": "string",
"description": "Only this app, e.g. skool."
}
},
"additionalProperties": false
}Clicks element `element`, or point `x`, `y` of the screenshot; `double` double-clicks, `button: right` right-clicks. Answers the page after it: the elements and text in view, with the same numbers. Says when nothing changed. A link that would open a new tab opens in this one. Buttons that pay or buy, and sign-in and account pages, are refused.
| Argument | Type | Description |
|---|---|---|
| x | number | Instead of `element`: pixels from the left of the screenshot. |
| y | number | With `x`: pixels from the top of the screenshot. |
| button | string | right opens the page's own context menu. Default: left. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| double | boolean | Double-click. |
| element | integer | The element's number from the last read or step answer. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
Ends the browser session when the task is done: the browser keeps its cookies and sleeps, and the per-minute charge stops. Answers the session's minutes and credits.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Gets the file that clicking `element` (a download link or button) or opening `url` starts: answers its name, type, size and a link valid 15 minutes; CSV, JSON and other text files also as text.
| Argument | Type | Description |
|---|---|---|
| url | string | A public http or https address, e.g. https://example.com. |
| element | integer | The element's number from the last read or step answer. |
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "A public http or https address, e.g. https://example.com."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"additionalProperties": false
}Drags from one element or point to another: a card between columns, a piece on a board, a slider's handle. Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| to* | object | An element number, or x and y of the screenshot. |
| from* | object | An element number, or x and y of the screenshot. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"type": "object",
"required": [
"from",
"to"
],
"properties": {
"to": {
"type": "object",
"properties": {
"x": {
"type": "number",
"minimum": 0,
"description": "Instead of `element`: pixels from the left of the screenshot."
},
"y": {
"type": "number",
"minimum": 0,
"description": "With `x`: pixels from the top of the screenshot."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"description": "An element number, or x and y of the screenshot.",
"additionalProperties": false
},
"from": {
"type": "object",
"properties": {
"x": {
"type": "number",
"minimum": 0,
"description": "Instead of `element`: pixels from the left of the screenshot."
},
"y": {
"type": "number",
"minimum": 0,
"description": "With `x`: pixels from the top of the screenshot."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"description": "An element number, or x and y of the screenshot.",
"additionalProperties": false
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
}Runs a JavaScript function body on the page and answers what it returns, as JSON. Use it to extract data the page holds (a table, a list, attributes); act with the other tools. It cannot send requests, click, submit, or read cookies or storage; a filled field's value reads [hidden by Cotlet]. Example: return [...document.querySelectorAll('h2')].map(h => h.innerText)
| Argument | Type | Description |
|---|---|---|
| script* | string | A function body that returns. |
{
"type": "object",
"required": [
"script"
],
"properties": {
"script": {
"type": "string",
"maxLength": 20000,
"description": "A function body that returns."
}
},
"additionalProperties": false
}Fills several fields in one step: text fields take text, drop-downs an option's label, checkboxes, radios and switches true or false. Stops at the first field that fails and names those filled. Does not send the form: click its button after. Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| fields* | array | The fields in the order a person fills them. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"type": "object",
"required": [
"fields"
],
"properties": {
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"fields": {
"type": "array",
"items": {
"type": "object",
"required": [
"element",
"value"
],
"properties": {
"value": {
"type": [
"string",
"boolean"
],
"description": "Text, option, or true/false."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"additionalProperties": false
},
"maxItems": 30,
"minItems": 1,
"description": "The fields in the order a person fills them."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
}Finds `text` on the whole current page, frames included: the elements whose label holds it, with their numbers, and each line of text that holds it. Use it instead of reading or scrolling a long page for one thing.
| Argument | Type | Description |
|---|---|---|
| kind | string | Only elements of this kind. Default: any. |
| text* | string | Words to look for, any case. |
{
"type": "object",
"required": [
"text"
],
"properties": {
"kind": {
"enum": [
"link",
"button",
"field",
"any"
],
"type": "string",
"description": "Only elements of this kind. Default: any."
},
"text": {
"type": "string",
"maxLength": 200,
"description": "Words to look for, any case."
}
},
"additionalProperties": false
}Rests the pointer on an element or a point, to open a hover menu, a tooltip or a preview. Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| x | number | Instead of `element`: pixels from the left of the screenshot. |
| y | number | With `x`: pixels from the top of the screenshot. |
| element | integer | The element's number from the last read or step answer. |
{
"type": "object",
"properties": {
"x": {
"type": "number",
"minimum": 0,
"description": "Instead of `element`: pixels from the left of the screenshot."
},
"y": {
"type": "number",
"minimum": 0,
"description": "With `x`: pixels from the top of the screenshot."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"additionalProperties": false
}Opens `url` in the current tab, or goes `history` back or forward. Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| url | string | A public http or https address, e.g. https://example.com. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| history | string | Instead of `url`. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "A public http or https address, e.g. https://example.com."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"history": {
"enum": [
"back",
"forward"
],
"type": "string",
"description": "Instead of `url`."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
}Starts the user's Google Discover Cloud Browser (a real Chrome on Cotlet, signed in to Google Discover as the user; use it for what the Google Discover tools do not cover) and opens `url`. Call it first. Only Google Discover pages open. Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| url | string | A public http or https address, e.g. https://example.com. |
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "A public http or https address, e.g. https://example.com."
}
},
"additionalProperties": false
}Presses a key on the focused element: Enter to send, Tab to the next field, Escape to close a pop-up, arrows in a list or slider, or one character (a site's shortcut). Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| key* | string | One of Enter, Tab, Shift+Tab, Escape, Backspace, Delete, Space, ArrowDown, ArrowUp, ArrowLeft, ArrowRight, PageDown, PageUp, Home, End, or one character such as a or 5. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| repeat | integer | Times to press it. Default 1. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"type": "object",
"required": [
"key"
],
"properties": {
"key": {
"type": "string",
"anyOf": [
{
"enum": [
"Enter",
"Tab",
"Shift+Tab",
"Escape",
"Backspace",
"Delete",
"Space",
"ArrowDown",
"ArrowUp",
"ArrowLeft",
"ArrowRight",
"PageDown",
"PageUp",
"Home",
"End"
]
},
{
"pattern": "^[ -~]$"
}
],
"description": "One of Enter, Tab, Shift+Tab, Escape, Backspace, Delete, Space, ArrowDown, ArrowUp, ArrowLeft, ArrowRight, PageDown, PageUp, Home, End, or one character such as a or 5."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"repeat": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Times to press it. Default 1."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
}The whole current page: its text (up to 20,000 characters) and a numbered list of its links, buttons, fields and other controls, open dialogs first. Use it on a new page or when a step's answer is not enough; `element` reads only inside one element (a dialog, a form, a list). Never returns field values, cookies or storage.
| Argument | Type | Description |
|---|---|---|
| element | integer | Read only inside this element. |
{
"type": "object",
"properties": {
"element": {
"type": "integer",
"minimum": 1,
"description": "Read only inside this element."
}
},
"additionalProperties": false
}A JPEG of the visible part of the page. Use it for boards, canvases, maps, charts and layout that the text does not show, then click or drag by `x`, `y` of the image.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Scrolls with the mouse wheel: `down` or `up` by `screens`, to `top` or `bottom`, until `element` is in view, or inside a panel or list (`inside`). Content that loads on scroll appears. Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| inside | integer | Scroll inside this element, not the page. |
| element | integer | Scroll until this element is in view. |
| screens | number | Viewport heights, for down and up. Default: 0.8. |
| direction | string | Default: down. |
{
"type": "object",
"properties": {
"inside": {
"type": "integer",
"minimum": 1,
"description": "Scroll inside this element, not the page."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "Scroll until this element is in view."
},
"screens": {
"type": "number",
"maximum": 10,
"description": "Viewport heights, for down and up. Default: 0.8.",
"exclusiveMinimum": 0
},
"direction": {
"enum": [
"down",
"up",
"top",
"bottom"
],
"type": "string",
"description": "Default: down."
}
},
"additionalProperties": false
}Chooses `option` (its label as listed, or its value) in drop-down `element`. For a home-made drop-down, click it, then click the option. Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| option* | string | The option. |
| element* | integer | The element's number from the last read or step answer. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
{
"type": "object",
"required": [
"element",
"option"
],
"properties": {
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"option": {
"type": "string",
"maxLength": 300,
"description": "The option."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
}Types `text` into field `element`, replacing what it held; `submit` presses Enter after it. For several fields use fill_form. Without `element` the text goes where the focus is, as a person types after clicking: for spreadsheet cells and editors that read does not number (Google Sheets, Docs), click the place first; there a tab in `text` presses Tab and a line break Enter, so one call fills a table. Answers the page after it: the elements and text in view, with the same numbers. Password, card and one-time code fields are refused: the user types them.
| Argument | Type | Description |
|---|---|---|
| text* | string | The text to type. |
| dialog | string | How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog. |
| slowly | boolean | Key by key, for a search or address field whose suggestions do not appear. |
| submit | boolean | Press Enter after typing, e.g. to search. |
| element | integer | The field's number from the last read. Leave it out to type where the focus is. |
| dialog_text | string | Text for a prompt dialog this step opens; implies accept. |
Puts files into file field or upload button `element`: each file is {"url": "https://..."} or {"file_id": "..."} of a file uploaded to Cotlet; up to 10 files, 20 MB each. Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| files* | array | The files. |
| element* | integer | The element's number from the last read or step answer. |
{
"type": "object",
"required": [
"element",
"files"
],
"properties": {
"files": {
"type": "array",
"items": {
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "A public file URL."
},
"file_id": {
"type": "string",
"description": "A file uploaded to Cotlet."
}
},
"additionalProperties": false
},
"maxItems": 10,
"minItems": 1,
"description": "The files."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
}
},
"additionalProperties": false
}Waits until `text` shows on the page (at most `seconds`, default 5, up to 20), or just `seconds`: for results that load slowly. Says whether the text appeared. Answers the page after it: the elements and text in view, with the same numbers.
| Argument | Type | Description |
|---|---|---|
| text | string | Text to wait for. |
| seconds | number | At most. |
{
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 200,
"description": "Text to wait for."
},
"seconds": {
"type": "number",
"maximum": 20,
"description": "At most.",
"exclusiveMinimum": 0
}
},
"additionalProperties": false
}Status of an earlier Cotlet call, by its call_id: pending (waits for the owner's approval in the Cotlet console), approved, running, success, rejected, expired, blocked or failed. For a call that answered with status pending or running.
| Argument | Type | Description |
|---|---|---|
| call_id* | string | call_id from the earlier call |
{
"type": "object",
"required": [
"call_id"
],
"properties": {
"call_id": {
"type": "string",
"description": "call_id from the earlier call"
}
},
"additionalProperties": false
}Sends a report to the Cotlet team: a tool that failed or returned wrong data, an error you could not get past, or a step the browser could not do, with the page, the step and what you saw. A missing dedicated tool is not a problem to report: do the task in the browser. A feature the user asks for goes as feature_request. A report promises nothing: tell the user it was sent, never that something will be built or fixed, or when. The report carries the error text and call_id when there is one, never passwords or tokens. Needs the user's Cotlet API key or sign-in.
| Argument | Type | Description |
|---|---|---|
| app | any | App slug the report is about, e.g. 'skool', or for a site in the web browser its host, e.g. 'app.example.com'. |
| kind* | string | bug: a tool did the wrong thing or returned wrong data. error: a call failed or returned an error you could not get past. feature_request: something new the user asked for. missing_feature: a step the task needed that you tried and could not do, in the browser or with a tool. other: anything else. |
| tool | any | Tool or endpoint name, e.g. 'skool_list_members'. |
| title* | string | One line, e.g. 'skool_list_members stops after 50 members'. |
| client | any | Agent or tool sending this, e.g. 'Claude Code'. |
| call_id | any | call_id of the call that went wrong, if any. |
Requests access to apps for the user's workspace, as Request access in the console: every app is granted at once. Not needed to work in an app: the user's AI works in any web app in their Web browser with cotlet_app_guide. An app with dedicated tools gets them after the user signs in to it in their Cloud Browser. Access says nothing about whether a task works there: check that in the browser. Takes app slugs as listed at https://cotlet.dev/api/v1/apps. Free. Needs the user's Cotlet API key or sign-in.
| Argument | Type | Description |
|---|---|---|
| apps* | array | App slugs, e.g. ["skool", "substack"]. |
| use_case | string | What the user wants the agent to do in these apps, in their words. |
{
"type": "object",
"required": [
"apps"
],
"properties": {
"apps": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"description": "App slugs, e.g. [\"skool\", \"substack\"]."
},
"use_case": {
"type": "string",
"maxLength": 1000,
"description": "What the user wants the agent to do in these apps, in their words."
}
},
"additionalProperties": false
}Returns a one-time upload_url and a file_id for a local file (an image for a post, an attachment). The file is sent to upload_url with an HTTP PUT; an argument that takes a file accepts {"file_id": "..."}. Up to 25 MB, the URL works once. Free. Needs the user's Cotlet API key or sign-in.
| Argument | Type | Description |
|---|---|---|
| name | string | File name, e.g. photo.jpg. |
| content_type | string | MIME type, e.g. image/jpeg. |
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "File name, e.g. photo.jpg."
},
"content_type": {
"type": "string",
"description": "MIME type, e.g. image/jpeg."
}
},
"additionalProperties": false
}The Cotlet account this connection acts as: email, workspace, access status, the API key or OAuth client in use with its scope, the apps the workspace may call and its credit balance. Free. Needs the user's Cotlet API key or sign-in.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}The cards Google Discover shows right now in a country, in feed order, with no Google account. Returns the Discover feed Chrome for Android shows on its New Tab page to someone who is not signed in to Google, read from a home IP in the country asked for: position, title, publisher, URL, domain, article or video, age as the card shows it, and the card image. It is the default feed of that country and language, not anyone's personal feed and not data from a panel of users. One read holds about 30 cards; the feed changes over the day, and a read is reused for up to 15 minutes per country and language.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many cards to return, counted from the top of the feed. Default: all (about 30). |
| country | string | Country of the feed, ISO 3166-1 alpha-2 (US, GB, DE, PL ...). The feed is read from a home IP there, so its stories are the ones Discover shows in that country. Default: US. |
| language | string | Language of the feed, BCP 47 (en-US, de-DE, pt-BR). Default: the country's main language. |
{
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "How many cards to return, counted from the top of the feed. Default: all (about 30)."
},
"country": {
"type": "string",
"pattern": "^[A-Za-z]{2}$",
"description": "Country of the feed, ISO 3166-1 alpha-2 (US, GB, DE, PL ...). The feed is read from a home IP there, so its stories are the ones Discover shows in that country. Default: US."
},
"language": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[A-Za-z]{2,4})?$",
"description": "Language of the feed, BCP 47 (en-US, de-DE, pt-BR). Default: the country's main language."
}
},
"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 9, 2026.
{
"type": "object",
"properties": {
"x": {
"type": "number",
"minimum": 0,
"description": "Instead of `element`: pixels from the left of the screenshot."
},
"y": {
"type": "number",
"minimum": 0,
"description": "With `x`: pixels from the top of the screenshot."
},
"button": {
"enum": [
"left",
"right"
],
"type": "string",
"description": "right opens the page's own context menu. Default: left."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"double": {
"type": "boolean",
"description": "Double-click."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The element's number from the last read or step answer."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
}{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"maxLength": 5000,
"description": "The text to type."
},
"dialog": {
"enum": [
"accept",
"dismiss"
],
"type": "string",
"description": "How to answer a native dialog (confirm, prompt, 'leave this page?') this step opens: accept presses OK, dismiss presses Cancel. Default: OK for an alert, Cancel for every other dialog."
},
"slowly": {
"type": "boolean",
"description": "Key by key, for a search or address field whose suggestions do not appear."
},
"submit": {
"type": "boolean",
"description": "Press Enter after typing, e.g. to search."
},
"element": {
"type": "integer",
"minimum": 1,
"description": "The field's number from the last read. Leave it out to type where the focus is."
},
"dialog_text": {
"type": "string",
"maxLength": 1000,
"description": "Text for a prompt dialog this step opens; implies accept."
}
},
"additionalProperties": false
}| description* |
| string |
| What the user asked for, what you tried, what you expected and what happened, with the error text if there was one. No passwords, tokens or other secrets. |
{
"type": "object",
"title": "AgentReportCreate",
"required": [
"kind",
"title",
"description"
],
"properties": {
"app": {
"anyOf": [
{
"type": "string",
"maxLength": 80
},
{
"type": "null"
}
],
"title": "App",
"default": null,
"description": "App slug the report is about, e.g. 'skool', or for a site in the web browser its host, e.g. 'app.example.com'."
},
"kind": {
"enum": [
"bug",
"error",
"feature_request",
"missing_feature",
"other"
],
"type": "string",
"title": "Kind",
"description": "bug: a tool did the wrong thing or returned wrong data. error: a call failed or returned an error you could not get past. feature_request: something new the user asked for. missing_feature: a step the task needed that you tried and could not do, in the browser or with a tool. other: anything else."
},
"tool": {
"anyOf": [
{
"type": "string",
"maxLength": 160
},
{
"type": "null"
}
],
"title": "Tool",
"default": null,
"description": "Tool or endpoint name, e.g. 'skool_list_members'."
},
"title": {
"type": "string",
"title": "Title",
"maxLength": 200,
"minLength": 3,
"description": "One line, e.g. 'skool_list_members stops after 50 members'."
},
"client": {
"anyOf": [
{
"type": "string",
"maxLength": 80
},
{
"type": "null"
}
],
"title": "Client",
"default": null,
"description": "Agent or tool sending this, e.g. 'Claude Code'."
},
"call_id": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"type": "null"
}
],
"title": "Call Id",
"default": null,
"description": "call_id of the call that went wrong, if any."
},
"description": {
"type": "string",
"title": "Description",
"maxLength": 5000,
"minLength": 10,
"description": "What the user asked for, what you tried, what you expected and what happened, with the error text if there was one. No passwords, tokens or other secrets."
}
},
"description": "Body of POST /api/v1/reports and the arguments of the MCP tool cotlet_report_issue.",
"additionalProperties": false
}