BrightLocal MCP Server and API by Cotlet
REMOTE · COTLET.DEV · 2 COMPONENTS
BrightLocal local SEO management MCP server: list locations, get rank tracker report.
Available components
Last scanned (15 hours ago)
Scores higher than 56% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Marketing and SEO
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security66
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (cotlet_browser_click). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability60
- 50% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 8145 tokens (~166/item across 49 items; 47 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
- Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 47 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 49 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Nov 26 −3
- The server rewrote its instructions, which are the text every model session reads security
- Tool “cotlet_browser_type” rewrote its description, which is the text the model reads security
- Schema quality: 100% → 50% ▼ functional
- New resource “cotlet-refresh-button” functional
- 19 Nov 26 0
- Tool “cotlet_upload_file” rewrote its description, which is the text the model reads security
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 147 → 166 ▼ functional
- “cotlet_browser_click” added an optional parameter “tab” cosmetic
- “cotlet_browser_download” added an optional parameter “tab” cosmetic
- “cotlet_browser_drag” added an optional parameter “tab” cosmetic
- “cotlet_browser_evaluate” added an optional parameter “tab” cosmetic
- “cotlet_browser_fill_form” added an optional parameter “tab” cosmetic
- “cotlet_browser_find” added an optional parameter “tab” cosmetic
- “cotlet_browser_hover” added an optional parameter “tab” cosmetic
- “cotlet_browser_navigate” added an optional parameter “tab” cosmetic
- “cotlet_browser_press” added an optional parameter “tab” cosmetic
- “cotlet_browser_read” added an optional parameter “tab” cosmetic
- “cotlet_browser_screenshot” added an optional parameter “tab” cosmetic
- “cotlet_browser_scroll” added an optional parameter “tab” cosmetic
- “cotlet_browser_select” added an optional parameter “tab” cosmetic
- “cotlet_browser_type” added an optional parameter “tab” cosmetic
- “cotlet_browser_upload” added an optional parameter “tab” cosmetic
- “cotlet_browser_wait” added an optional parameter “tab” cosmetic
- 16 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “cotlet_whoami” rewrote its description, which is the text the model reads security
- 14 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://cotlet.dev/mcp/v1/brightlocal
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=cotlet.dev | CN=YE1,O=Let's Encrypt,C=US | 12 Oct 2026 | 10 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 6afd7585ee8e24a40f5683c10835ec990a8 |
| SANs: *.cotlet.dev, cotlet.dev | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of cotlet.dev. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | DS published | 60074 | 8 | Verified |
| cotlet.dev. | DS published | 2371 | 13 | Verified |
| cotlet.dev. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| x-content-type-options | nosniff |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://cotlet.dev/mcp/v1/brightlocal | Verified | 200 | |
| http (plaintext) | http://cotlet.dev/mcp/v1/brightlocal | HTTPS enforced | 301 | https://cotlet.dev/mcp/v1/brightlocal |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
brightlocal_get_local_search_grid_report Get local search grid report in BrightLocal ~99
Get local search grid report in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
brightlocal_get_rank_tracker_report Get rank tracker report in BrightLocal ~97
Get rank tracker report in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
brightlocal_list_locations List locations in BrightLocal ~93
List locations in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
brightlocal_list_reviews List reviews in BrightLocal ~93
List reviews in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
brightlocal_re_run_report Re-run report in BrightLocal ~95
Re-run report in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
brightlocal_update_rank_tracker_keywords Update rank tracker keywords in BrightLocal ~97
Update rank tracker keywords in the user's own BrightLocal account from ChatGPT, Claude or any AI agent. Returns how to do it in BrightLocal step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's BrightLocal Cloud Browser. BrightLocal's official API: BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
cotlet_app_guide Cotlet: how to work in an app ~180
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. For BrightLocal it covers these actions: List locations, Get rank tracker report, Get local search grid report, List reviews, Update rank tracker keywords, Re-run report.
| Name | Type | Req | Description |
|---|---|---|---|
| app | string | – | The app's name or Cotlet slug. Default: BrightLocal. |
| task | string | – | What the user wants done in the app, in their words. |
No output schema declared.
No examples provided.
cotlet_apps Cotlet: apps I can use ~85
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.
| Name | Type | Req | Description |
|---|---|---|---|
| app | string | – | Only this app, e.g. skool. |
No output schema declared.
No examples provided.
cotlet_browser_click Click on the page ~300
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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. |
| dialog_text | string | – | Text for a prompt dialog this step opens; implies accept. |
| double | boolean | – | Double-click. |
| element | integer | – | The element's number from the last read or step answer. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
| x | number | – | Instead of `element`: pixels from the left of the screenshot. |
| y | number | – | With `x`: pixels from the top of the screenshot. |
No output schema declared.
No examples provided.
cotlet_browser_close Close the browser ~43
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
cotlet_browser_download Download a file ~160
Gets the file that clicking `element` (a download link or button) or opening `url` starts, also an image or PDF it only opens: answers its name, type, size and a link valid 15 minutes; CSV, JSON and other text files also as text.
| Name | Type | Req | Description |
|---|---|---|---|
| element | integer | – | The element's number from the last read or step answer. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
| url | string | – | A public http or https address, e.g. https://example.com. |
No output schema declared.
No examples provided.
cotlet_browser_drag Drag on the page ~211
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.
| Name | Type | Req | 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. |
| dialog_text | string | – | Text for a prompt dialog this step opens; implies accept. |
| from | object | yes | An element number, or x and y of the screenshot. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
| to | object | yes | An element number, or x and y of the screenshot. |
No output schema declared.
No examples provided.
cotlet_browser_evaluate Run a script on the page ~165
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)
| Name | Type | Req | Description |
|---|---|---|---|
| script | string | yes | A function body that returns. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
No output schema declared.
No examples provided.
cotlet_browser_fill_form Fill in a form ~220
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.
| Name | Type | Req | 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. |
| dialog_text | string | – | Text for a prompt dialog this step opens; implies accept. |
| fields | array | yes | The fields in the order a person fills them. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
No output schema declared.
No examples provided.
cotlet_browser_find Find on the page ~141
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.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | – | Only elements of this kind. Default: any. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
| text | string | yes | Words to look for, any case. |
No output schema declared.
No examples provided.
cotlet_browser_hover Point at the page ~160
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.
| Name | Type | Req | Description |
|---|---|---|---|
| element | integer | – | The element's number from the last read or step answer. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
| x | number | – | Instead of `element`: pixels from the left of the screenshot. |
| y | number | – | With `x`: pixels from the top of the screenshot. |
No output schema declared.
No examples provided.
cotlet_browser_navigate Go to a page ~200
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.
| Name | Type | Req | 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. |
| dialog_text | string | – | Text for a prompt dialog this step opens; implies accept. |
| history | string | – | Instead of `url`. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
| url | string | – | A public http or https address, e.g. https://example.com. |
No output schema declared.
No examples provided.
cotlet_browser_open Open the browser ~134
Starts the user's BrightLocal Cloud Browser (a real Chrome on Cotlet, signed in to BrightLocal as the user; use it for what the BrightLocal tools do not cover) and opens `url`. Call it first. Only BrightLocal pages open. Answers the page after it: the elements and text in view, with the same numbers. In BrightLocal it serves these actions: List locations, Get rank tracker report, Get local search grid report, List reviews, Update rank tracker keywords, Re-run report.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | – | A public http or https address, e.g. https://example.com. |
No output schema declared.
No examples provided.
cotlet_browser_press Press a key ~262
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.
| Name | Type | Req | 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. |
| dialog_text | string | – | Text for a prompt dialog this step opens; implies accept. |
| key | string | yes | 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. |
| repeat | integer | – | Times to press it. Default 1. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
No output schema declared.
No examples provided.
cotlet_browser_read Read the page ~154
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.
| Name | Type | Req | Description |
|---|---|---|---|
| element | integer | – | Read only inside this element. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
No output schema declared.
No examples provided.
cotlet_browser_screenshot See the page ~110
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.
| Name | Type | Req | Description |
|---|---|---|---|
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
No output schema declared.
No examples provided.
cotlet_browser_scroll Scroll the page ~193
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.
| Name | Type | Req | Description |
|---|---|---|---|
| direction | string | – | Default: down. |
| element | integer | – | Scroll until this element is in view. |
| inside | integer | – | Scroll inside this element, not the page. |
| screens | number | – | Viewport heights, for down and up. Default: 0.8. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
No output schema declared.
No examples provided.
cotlet_browser_select Choose from a list ~212
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.
| Name | Type | Req | 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. |
| dialog_text | string | – | Text for a prompt dialog this step opens; implies accept. |
| element | integer | yes | The element's number from the last read or step answer. |
| option | string | yes | The option. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
No output schema declared.
No examples provided.
cotlet_browser_type Type on the page ~334
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. A password or code the user gave you goes in like any text; card fields are refused.
| Name | Type | Req | 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. |
| dialog_text | string | – | Text for a prompt dialog this step opens; implies accept. |
| element | integer | – | The field's number from the last read. Leave it out to type where the focus is. |
| 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. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
| text | string | yes | The text to type. |
No output schema declared.
No examples provided.
cotlet_browser_upload Upload a file ~158
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.
| Name | Type | Req | Description |
|---|---|---|---|
| element | integer | yes | The element's number from the last read or step answer. |
| files | array | yes | The files. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
No output schema declared.
No examples provided.
cotlet_browser_wait Wait for the page ~144
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.
| Name | Type | Req | Description |
|---|---|---|---|
| seconds | number | – | At most. |
| tab | string | – | The Tab id of the last answer. The step acts only while that tab is the shown one; if the user or another client showed another tab, it does nothing and answers tab_changed. Leave it out to act on th… |
| text | string | – | Text to wait for. |
No output schema declared.
No examples provided.
cotlet_get_call Cotlet: check a call ~76
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.
| Name | Type | Req | Description |
|---|---|---|---|
| call_id | string | yes | call_id from the earlier call |
No output schema declared.
No examples provided.
cotlet_report_issue Cotlet: report a bug or a missing feature ~364
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.
| Name | Type | Req | Description |
|---|---|---|---|
| app | – | – | App slug the report is about, e.g. 'skool', or for a site in the web browser its host, e.g. 'app.example.com'. |
| call_id | – | – | call_id of the call that went wrong, if any. |
| client | – | – | Agent or tool sending this, e.g. 'Claude Code'. |
| description | string | yes | 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. |
| kind | string | yes | 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 th… |
| title | string | yes | One line, e.g. 'skool_list_members stops after 50 members'. |
| tool | – | – | Tool or endpoint name, e.g. 'skool_list_members'. |
No output schema declared.
No examples provided.
cotlet_request_apps Cotlet: request access to apps ~170
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.
| Name | Type | Req | Description |
|---|---|---|---|
| apps | array | yes | App slugs, e.g. ["skool", "substack"]. |
| use_case | string | – | What the user wants the agent to do in these apps, in their words. |
No output schema declared.
No examples provided.
cotlet_upload_file Cotlet: upload a file for a tool ~125
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 takes one stored file (a failed PUT can be sent again). Free. Needs the user's Cotlet API key or sign-in.
| Name | Type | Req | Description |
|---|---|---|---|
| content_type | string | – | MIME type, e.g. image/jpeg. |
| name | string | – | File name, e.g. photo.jpg. |
No output schema declared.
No examples provided.
cotlet_whoami Cotlet: who am I ~80
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, its credit balance, and the app the user signed up for with its first task and sign-in link. Free. Needs the user's Cotlet API key or sign-in.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_citation_tracker_report Get a Citation Tracker report ~152
Read a Citation Tracker report: where the business is listed, missing, or listed with wrong NAP data. Returns the top-site coverage and citation score, name, address, postcode and phone accuracy counts, the competitors' citation counts and the citations themselves: site, type, authority, whether the business is listed and with which name, address and phone, the fields that do not match, duplicates and whether Citation Builder can submit to that site. Top sites first, then by authority.
| Name | Type | Req | Description |
|---|---|---|---|
| filter | string | – | Which citations to return. Default all. |
| limit | integer | – | Most citations returned, default 100. |
| report_id | integer | yes | report_id from list_citation_tracker_reports. |
No output schema declared.
No examples provided.
get_gbp_audit Get the Google Business Profile Audit ~145
Read a location's Google Business Profile Audit: profile data, NAP check, local ranking factors. Returns the audited Google Business Profile (name, address, phone, website, category, description, verified, rating, reviews, photos, hours) and what changed since the last run, how the profile's name, address, postcode and phone match the location, local ranking factors, duplicates, recent reviews and, per keyword, the location's local rank with the top competitors. A location without a Google Business Profile has no audit: `audit` is null and `note` says what to set up.
| Name | Type | Req | Description |
|---|---|---|---|
| location_id | integer | yes | location_id from list_locations. |
No output schema declared.
No examples provided.
get_local_search_grid_report Get a Local Search Grid report ~182
Read a location's Local Search Grid: the Google Maps rank at each grid point, and competitors. Returns the grid (size, points, distance, center), the average rank over all keywords, each keyword's latest run (average rank, points ranked 1-3, 4-10, 11+), and for one keyword and run (the first keyword and the latest run unless given) the rank at every grid point and the top 10 competitors. A location without a Google Business Profile has no grid: `report` is null and `note` says what to set up.
| Name | Type | Req | Description |
|---|---|---|---|
| keyword | string | – | A keyword of the report. Default: the first. |
| location_id | integer | yes | location_id from list_locations. |
| run_id | string | – | A run from the keyword's `runs`. Default: the latest. |
No output schema declared.
No examples provided.
get_location Get a location ~87
Read one location's business details: name, address, phone, website, category, hours, descriptions. Returns the record BrightLocal compares citations and listings against (NAP): business name, address, phones, website, category, contact person, short and long description, year founded, employees, payment methods, services and opening hours.
| Name | Type | Req | Description |
|---|---|---|---|
| location_id | integer | yes | location_id from list_locations. |
No output schema declared.
No examples provided.
get_rank_tracker_report Get a rank tracker report ~157
Read a Rank Tracker report: each keyword's position on Google, Maps and the local pack, with changes. Returns one run of the report (the latest unless run_id is given) against the run before it: per keyword the search volume and, per search engine, the rank (null = not in the top 50), previous rank, change and ranking URL; the keywords up, down, gained and lost; the competitors tracked. `runs` lists every run.
| Name | Type | Req | Description |
|---|---|---|---|
| location_id | integer | yes | location_id of the report, from list_rank_tracker_reports. |
| report_id | integer | yes | report_id from list_rank_tracker_reports. |
| run_id | integer | – | A run from `runs`. Default: the latest. |
No output schema declared.
No examples provided.
get_review_summary Get the review summary ~111
Read a location's star rating and review counts overall and per review site. Returns the average star rating and total reviews over all tracked sites, the count per star rating, and per site with a listing: its rating, total, new reviews, reviews in the last 30 days, this and last month and this year, and the profile link. A location without a Reputation Manager report (BrightLocal Grow plan) answers zeros and a note.
| Name | Type | Req | Description |
|---|---|---|---|
| location_id | integer | yes | location_id from list_locations. |
No output schema declared.
No examples provided.
list_active_sync_alerts List Active Sync alerts ~118
List Active Sync alerts: changes found on a location's listings on other sites. Each alert is a field (name, address, phone, website, category, description) whose value on an external listing (Google Business Profile, Facebook, Bing, Apple Maps, Yelp) differs from the location's data in BrightLocal. Alerts appear only for locations with Active Sync connections. new_alerts counts the unseen ones.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous call. |
| query | string | – | Location name to search for. |
No output schema declared.
No examples provided.
list_citation_builder_campaigns List Citation Builder campaigns ~147
List Citation Builder campaigns with their status, from Saved to Submitting To Sites and Complete. One row per campaign: location, status (Saved, Reviewing Data, On Hold, Submitting To Sites, Live Listing Checks, Complete), payment date, number of listings ordered, data aggregators and alerts. Saved campaigns are not paid or submitted yet. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues; total counts all campaigns.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous call. |
| location_id | integer | – | Only campaigns of this location. |
| status | string | – | Only campaigns in this status. |
No output schema declared.
No examples provided.
list_citation_tracker_reports List Citation Tracker reports ~128
List Citation Tracker reports with their last run, live citations and competitor citations. One row per report: location, reference, schedule, last run, the number of live citations (found and indexed by Google) and of competitor citations (sites your competitors are listed on). Read a report with get_citation_tracker_report. 20 per page. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous call. |
| location_id | integer | – | Only reports of this location. |
No output schema declared.
No examples provided.
list_local_search_grid_reports List Local Search Grid reports ~146
List Local Search Grid reports: keywords, grid size and the average Google Maps rank across the grid. One row per report: location, keywords, schedule, last run, status, grid size and points, average rank over all keywords and its change, credits a manual re-run costs. Local Search Grid needs the location's Google Business Profile, so locations without one have no rows. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues. Read a grid with get_local_search_grid_report.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous call. |
| location_id | integer | – | Only reports of this location. |
No output schema declared.
No examples provided.
list_locations List locations ~164
List the locations in the account with their rank, citation and review metrics, as on All Locations. Returns each location with its location_id, name, reference, city, status (active or ad_hoc) and the metrics of the All Locations page: average Google position and its change, rankings up, down and new, Local Search Grid average, citation score, live citations, star rating, total and recent reviews, Active Sync alerts. `reports` says which tools have a report on the location. 50 per page.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous call. |
| query | string | – | Business name, reference or zip code to search for. |
| status | string | – | Only locations in this state. Default: active and ad_hoc. |
No output schema declared.
No examples provided.
list_rank_tracker_reports List rank tracker reports ~142
List Rank Tracker reports with their latest run and average Google position. One row per report: location, schedule (ad_hoc, weekly, monthly), date of the latest run, status, average Google position and its change, keywords and positions moved. average_google_position is null when no keyword ranks in the top 50. location_id filters each page after BrightLocal returns it, so a page can come back short while next_cursor continues; total counts all reports. Read a report with get_rank_tracker_report and its location_id.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous call. |
| location_id | integer | – | Only reports of this location. |
No output schema declared.
No examples provided.
list_reviews List reviews ~224
List a location's reviews from all tracked review sites, newest first, with rating, text and status. Returns reviews Reputation Manager collected for the location: date, star rating, reviewer, site, text, status (unread, action_required, do_not_respond, manually_responded, auto_responded, pending_removal, successfully_removed, removal_failed) and whether BrightLocal can post a reply (can_reply, needs a connected Google Business Profile or Facebook page). Filter by rating and site. A location without a Reputation Manager report (BrightLocal Grow plan, with the Google Business Profile or Facebook page connected) answers an empty list and a note.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous call. |
| limit | integer | – | Reviews per page, default 25. |
| location_id | integer | yes | location_id from list_locations. |
| rating | array | – | Only reviews with these star ratings, e.g. [1, 2]. |
| source | string | – | Only this review site, e.g. google, yelp, facebook. |
No output schema declared.
No examples provided.
rerun_report Re-run a report ~153
Run one of a location's reports now, as the Re-run button does. Starts a manual run of the location's report of that type, as the Re-run button does. A manual run uses one of the account's ad-hoc run credits; a Local Search Grid run also uses grid credits. After a trial ends BrightLocal stops runs. local_search_grid and gbp_audit need the location's Google Business Profile, reputation_manager needs Reputation Manager (Grow plan); without them the call is refused with the reason. The run takes minutes; read the report afterwards.
| Name | Type | Req | Description |
|---|---|---|---|
| location_id | integer | yes | location_id from list_locations. |
| report_type | string | yes | Which of the location's reports to run. |
No output schema declared.
No examples provided.
respond_to_review Reply to a review ~139
Post a public reply to a review on Google or Facebook through BrightLocal. Publishes the text as the business's reply under the review on its site and marks the review Manually Responded. Only reviews with can_reply true in list_reviews accept a reply: the location needs a connected Google Business Profile or Facebook page. The reviewer and anyone reading the review see it. The review must be among the location's latest 1000. Waits for the owner's approval.
| Name | Type | Req | Description |
|---|---|---|---|
| location_id | integer | yes | location_id from list_locations. |
| review_id | integer | yes | review_id from list_reviews. |
| text | string | yes | The public reply. |
No output schema declared.
No examples provided.
update_rank_tracker_keywords Update rank tracker keywords ~114
Add or remove keywords tracked by a location's Rank Tracker report. Changes the keyword list of the location's Rank Tracker report and saves the report with its other settings unchanged. Up to 100 keywords per report. Keywords already tracked are not added twice. New keywords get positions on the next scheduled run, or now with rerun_report.
| Name | Type | Req | Description |
|---|---|---|---|
| add | array | – | Keywords to start tracking. |
| location_id | integer | yes | location_id of the Rank Tracker report. |
| remove | array | – | Keywords to stop tracking. |
No output schema declared.
No examples provided.
How do I install the BrightLocal MCP Server and API by Cotlet server?
BrightLocal MCP Server and API by Cotlet is a hosted endpoint at https://cotlet.dev/mcp/v1/brightlocal, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · cotlet.dev
claude mcp add --transport http dev-cotlet-brightlocal 'https://cotlet.dev/mcp/v1/brightlocal'
What is the BrightLocal MCP Server and API by Cotlet server?
BrightLocal MCP Server and API by Cotlet is listed in the public MCP registry as dev.cotlet/brightlocal. BrightLocal local SEO management MCP server: list locations, get rank tracker report. This page covers its hosted endpoint (https://cotlet.dev/mcp/v1/brightlocal).
Is the BrightLocal MCP Server and API by Cotlet server safe to use?
BrightLocal MCP Server and API by Cotlet scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the BrightLocal MCP Server and API by Cotlet server expose?
BrightLocal MCP Server and API by Cotlet exposes 47 tools: cotlet_whoami, cotlet_apps, cotlet_request_apps, cotlet_get_call, cotlet_upload_file, and 42 more. Their descriptions and schemas cost roughly 7,264 tokens of context every time the server is loaded.
Does the BrightLocal MCP Server and API by Cotlet server require authentication?
No. We connected to BrightLocal MCP Server and API by Cotlet without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the BrightLocal MCP Server and API by Cotlet server still maintained?
BrightLocal MCP Server and API by Cotlet is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the BrightLocal MCP Server and API by Cotlet server?
VerifyMCP ran 13 checks on BrightLocal MCP Server and API by Cotlet, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.