BrightLocal MCP Server
Local rankings, map grids, reviews and citations in BrightLocal, worked by your agent.
Hosted MCP Server
npx add-mcp 'https://cotlet.dev/mcp/v1/brightlocal'Installs into Claude Code, Codex, Cursor and more
Documentation
Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up
BrightLocal API and MCP server: Let your AI agent watch your local rankings.
BrightLocal has a REST API and an official MCP server, BrightLocal Anywhere, whose read-write connections update and run reports but do not reply to reviews (checked 27 Oct 2026). Cotlet runs 16 BrightLocal tools hosted, over MCP for agents and REST for scripts, and three of them write.
Read BrightLocal locations and report metrics through MCP or REST. Connect your AI agent, n8n, Make, Zapier or a script to the locations your account can access.
Connect an AI agent Use the REST API
- Free 7-day trial, no card
- Unofficial, not affiliated with BrightLocal
- Page: https://cotlet.dev/integrations/brightlocal-api-mcp-server
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by BrightLocal. BrightLocal is a trademark of its owner. If BrightLocal's own integrations cover what you need, use them first.
What can you automate in BrightLocal?
- Check rankings for your services
- Read new reviews, draft replies
- Track a new service keyword
- Run a report now
- Find listings with a wrong phone
- See your map grid and competitors
Does BrightLocal have an MCP server or an API?
- BrightLocal Anywhere needs an active Grow plan and access to BrightLocal Labs.
- The REST API needs an API key from BrightLocal support and a developer to build on it.
- Reviews need Reputation Manager, which BrightLocal sells in its Grow plan. The Local Search Grid and the Google Business Profile Audit need your Google Business Profile connected in BrightLocal.
| What you need | Official MCP server | REST API | Cotlet |
|---|---|---|---|
| Read rankings, reviews, citations | Yes, Grow plan and Labs | Yes, with a key | Yes |
| Add or remove tracked keywords | Yes, read-write connection | Yes, you write the code | Yes |
| Re-run a report | Yes, read-write connection | Yes, you write the code | Yes |
| Reply to a Google review | No tool found | Not in the pages we checked | Yes, after your OK |
| Read Active Sync alerts | Yes, Grow plan and Labs | Not found | Yes |
| Fixed for you when BrightLocal changes | By BrightLocal | Your developer | Yes |
Checked 27 Oct 2026. Sources: BrightLocal Help: Is BrightLocal Anywhere secure?, BrightLocal Help: How do I get started with BrightLocal Anywhere?, BrightLocal Help: Does BrightLocal provide APIs?, BrightLocal: What is BrightLocal's MCP Server?, BrightLocal in the Claude directory (third-party mirror)
How does Cotlet connect to BrightLocal?
- Sign in to BrightLocal. Once, in a browser we keep for you.
- Choose MCP or REST. Connect your agent or create an API key.
- Run your workflow. Ask your agent or call the REST API.
We never save your BrightLocal password, and a review reply waits for your OK.
Connect BrightLocal to your AI agent or workflow
Use MCP with ChatGPT, Claude, Cursor or Codex, or authenticated HTTP in n8n, Make or Zapier. The REST guide follows the agent setup.
- Turn on BrightLocal for agents. Create a Cotlet account, sign in to BrightLocal in its Cloud Browser and press Enable for agents.
- Add the Cotlet address. Put https://cotlet.dev/mcp/v1/brightlocal in the MCP or connector settings of your agent.
- Sign in or use a key. Chat apps ask you to sign in to Cotlet. Editors and scripts use an API key from the console.
You need your own BrightLocal account first: the 14-day trial has full access and asks for no card (checked 27 Oct 2026). One connection carries every app you enable, BrightLocal among them. If you enabled BrightLocal after connecting, refresh the connector so your agent sees the new tools.
Claude:
Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect
Claude Code:
claude mcp add --transport http cotlet \
https://cotlet.dev/mcp/v1/brightlocal \
--header "Authorization: Bearer $COTLET_API_KEY"
ChatGPT:
Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth
Cursor:
// ~/.cursor/mcp.json
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1/brightlocal",
"headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
}
}
}
Codex:
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1/brightlocal"
bearer_token_env_var = "COTLET_API_KEY"
n8n:
MCP Client Tool (inside an AI Agent)
Transport: HTTP Streamable
URL: https://cotlet.dev/mcp/v1
Auth: Bearer, <your key>
Tool: brightlocal_read
Make, Zapier:
Make: MCP Client > Call a tool
Zapier: MCP Client by Zapier > Run Tool
Server URL: https://cotlet.dev/mcp/v1
Token: <your key>
Tool: brightlocal_write
How to use the BrightLocal REST API
Create your Cotlet API key
Sign in to BrightLocal in its Cloud Browser and enable it for agents. Create a Cotlet API key scoped to BrightLocal; read-only access is enough for these requests.
Calls use the permissions of your signed-in account.
Save your key as COTLET_API_KEY in your environment. Send Authorization: Bearer <your Cotlet API key>; never use an app password or cookie as the key.
Make your first BrightLocal API request
This GET request reads data without changing it.
cURL: first read:
curl https://cotlet.dev/api/v1/brightlocal/locations \
-H "Authorization: Bearer $COTLET_API_KEY"
A successful REST response puts the tool output in result. This example response excerpt omits call IDs, messages and credit details.
Example response excerpt:
{
"status": "success",
"app": "brightlocal",
"tool": "list_locations",
"result": {
"locations": [
{
"location_id": 4185522,
"name": "Example Plumbing",
"status": "active",
"metrics": {},
"reports": {}
}
],
"total": 1,
"next_cursor": null
}
}
Read locations and follow the cursor
Read result.locations and pass result.next_cursor as cursor until it is null, keeping query and status unchanged. Page size comes from BrightLocal.
By default, active and ad_hoc locations are included and demo locations are excluded. Metrics can be null when a report has no data; that does not make the location read fail.
Use get_location with a positive location_id from the list to read NAP details, hours and timezone.
BrightLocal workflows with n8n, Make and Zapier
| Tool | Connect through | Example workflow |
|---|---|---|
| n8n | HTTP Request | Read location metrics on a schedule and save a sheet snapshot keyed by location ID. |
| Make | HTTP > Make a request | Compare saved NAP details with the current location and send changes to your team. |
| Zapier | Webhooks by Zapier > GET or Custom Request | Export active locations into your reporting tool, matching by location ID. |
Configure the schedule, destination and saved state in your automation tool. Cotlet reads the source; your configured destination step writes the report or sends the alert.
Compare existing record state as well as IDs when detecting changes. Python and Node.js can use the same HTTP endpoints without an SDK or agent.
Endpoint and tool reference. The REST API guide covers requests, errors and approvals.
BrightLocal API endpoints and MCP tools
Locations
list_locations gives the location_id every other tool needs, with its rank, citation and review numbers.
- List locations (
list_locations, read): List the locations in the account with their rank, citation and review metrics, as on All Locations. - Get a location (
get_location, read): Read one location's business details: name, address, phone, website, category, hours, descriptions.
Rank Tracker
A null rank means the keyword is not in the top 50. New keywords get positions on the next run, or now with rerun_report.
- List rank tracker reports (
list_rank_tracker_reports, read): List Rank Tracker reports with their latest run and average Google position. - Get a rank tracker report (
get_rank_tracker_report, read): Read a Rank Tracker report: each keyword's position on Google, Maps and the local pack, with changes. - Update rank tracker keywords (
update_rank_tracker_keywords, write): Add or remove keywords tracked by a location's Rank Tracker report. - Re-run a report (
rerun_report, write): Run one of a location's reports now, as the Re-run button does.
Map grid and Google profile
These two need the location's Google Business Profile connected in BrightLocal. Without it they answer null and say what to set up.
- List Local Search Grid reports (
list_local_search_grid_reports, read): List Local Search Grid reports: keywords, grid size and the average Google Maps rank across the grid. - Get a Local Search Grid report (
get_local_search_grid_report, read): Read a location's Local Search Grid: the Google Maps rank at each grid point, and competitors. - Get the Google Business Profile Audit (
get_gbp_audit, read): Read a location's Google Business Profile Audit: profile data, NAP check, local ranking factors.
Reviews
Reputation Manager, a Grow plan feature. A reply needs a connected Google Business Profile or Facebook page.
- Get the review summary (
get_review_summary, read): Read a location's star rating and review counts overall and per review site. - List reviews (
list_reviews, read): List a location's reviews from all tracked review sites, newest first, with rating, text and status. - Reply to a review (
respond_to_review, write, asks first): Post a public reply to a review on Google or Facebook through BrightLocal.
Citations and alerts
Where the business is listed, with the name, address or phone that do not match, plus Citation Builder campaigns and Active Sync alerts.
- List Citation Tracker reports (
list_citation_tracker_reports, read): List Citation Tracker reports with their last run, live citations and competitor citations. - Get a Citation Tracker report (
get_citation_tracker_report, read): Read a Citation Tracker report: where the business is listed, missing, or listed with wrong NAP data. - List Citation Builder campaigns (
list_citation_builder_campaigns, read): List Citation Builder campaigns with their status, from Saved to Submitting To Sites and Complete. - List Active Sync alerts (
list_active_sync_alerts, read): List Active Sync alerts: changes found on a location's listings on other sites.
Inputs, REST path and example response of every tool: https://cotlet.dev/integrations/brightlocal-api-mcp-server#tools
Who can see my BrightLocal session, and how do I revoke it?
- What we store. Your signed-in BrightLocal profile, encrypted with AES-256-GCM in Finland. No password.
- What your agent gets. The 16 BrightLocal tools. Never the cookie, the token or the login.
- What the session sees. What your BrightLocal login sees: locations, business details, rankings, reviews, citations and alerts.
- What no tool touches. Your password, your plan, billing and users, and buying citations.
- If BrightLocal signs you out. Your agent gets a link to sign in again. We never type your password.
- How to cut access. Disable BrightLocal for agents, reset its browser or delete the key. The next call is refused.
A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results).
Approvals, undo and mistakes
- Reads the reviews. Lists the newest reviews with their rating, site and whether BrightLocal can post a reply.
- Drafts the reply. Writes the text in chat. Nothing is posted.
- Waits for your OK. A reply is a request in your Cotlet console.
- Posts it. BrightLocal publishes the reply on Google or Facebook and marks the review Manually Responded.
| Action | Undo |
|---|---|
| Add a keyword to the Rank Tracker | update_rank_tracker_keywords with remove |
| Remove a keyword | Add it back; its earlier positions stay in the old runs |
| Re-run a report | No. The run uses one of your ad-hoc run credits |
| Reply to a review | No. Reviewers and readers see it; delete it on the review site |
1 of 16 tools ask first: respond_to_review. The other 15 run at once: 13 only read, and update_rank_tracker_keywords and rerun_report change your report without asking.
rerun_report spends an ad-hoc run credit and does not ask. Tell your agent to confirm with you in chat before it runs many reports.
MCP call:
{
"name": "get_review_summary",
"arguments": {
"location_id": 4185522
}
}
REST:
curl https://cotlet.dev/api/v1/brightlocal/locations/4185522/review-summary \
-H "Authorization: Bearer $COTLET_API_KEY"
Tool output:
{
"location_id": 4185522,
"report_id": 542909,
"average_rating": 4.7,
"total_reviews": 52,
"by_rating": {
"1": 1,
"2": 1,
"3": 2,
"4": 6,
"5": 42
},
"sites": [
{
"source": "google",
"name": "Google",
"average_rating": 4.8,
"total": 41,
"new": 1,
"last_30_days": 3,
"this_month": 2,
"last_month": 3,
"this_year": 22,
"profile_url": "https://local.google.com/place?id=10000000000000000001&use=srp&hl=en"
},
{
"source": "yelp",
"name": "Yelp",
"average_rating": 4.2,
"total": 11,
"new": 0,
"last_30_days": 0,
"this_month": 0,
"last_month": 1,
"this_year": 3,
"profile_url": "https://www.yelp.com/biz/anderson-plumbing-and-drain"
}
],
"note": null
}
REST under /api/v1/brightlocal takes the same tools from scripts and cron jobs, with the same key and price. The tools table lists the REST path of each tool.
How much do the BrightLocal API and MCP server cost?
About $13 a month for a one-location service business, 2,320 credits.
| Job | Calls | Credits |
|---|---|---|
| Rank check, weekly | 3 × 4 | 120 |
| New reviews and drafts, daily | 2 × 30 | 600 |
| Keyword change and run, twice a month | 3 × 2 | 60 |
| Listings and Active Sync check, monthly | 4 × 1 | 40 |
| Cloud Browser, 30 days | 1,500 | |
| Total | 2,320 |
- Free 7-day trial, no card
- 10 credits per successful call, MCP or REST
- 50 credits a day for the Cloud Browser
- Packs valid 12 months, no subscription
BrightLocal publishes no figure for calls per business, so the month is our example: a weekly rank check, a daily look at new reviews, two keyword changes with a run and one monthly listing check. The browser is most of the bill. BrightLocal itself is billed by BrightLocal and has its own plans, with Reputation Manager in Grow (brightlocal.com/pricing, 27 Oct 2026). Dollars at the $29 pack rate.
BrightLocal MCP server, REST API or hosted: which to use
| Option | What it does | Where it stops |
|---|---|---|
| BrightLocal Anywhere | The official MCP server. Answers questions about your locations, rankings, reviews and citations. | Read-only. Needs the Grow plan and Labs access. |
| BrightLocal REST API | Management and data APIs for reports, keywords and results. | You need an API key from BrightLocal support and code you run and fix yourself. |
Pick BrightLocal Anywhere if you only want answers and your plan includes it. Pick the REST API if you have a developer and want to own the code. Pick Cotlet if an agent should also add keywords, run reports or draft and post review replies, or read Active Sync alerts.
Who runs Cotlet
Take Group sp. z o.o. runs Cotlet. It is a software company registered in Poland, EU (VAT PL6342984273), and has worked since 2019. Its founders are Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Write to contact@cotlet.dev with questions about the BrightLocal tools.
BrightLocal API and MCP server: questions
Can I use the API without an AI agent?
Yes. Use a scoped Cotlet API key and the signed-in BrightLocal Cloud Browser session. You do not need to connect MCP for REST. Start with the REST guide.
Can I use n8n, Make or Zapier?
Yes. Use authenticated HTTP requests with your Cotlet key, or an MCP client for agent workflows. You configure the schedule, destination and record state. See app-specific workflows.
How do I get access?
Sign up free at https://cotlet.dev, open BrightLocal under Integrations in the console and sign in to BrightLocal in its Cloud Browser. The free trial starts when you sign up and needs no card.
How do I connect BrightLocal to ChatGPT or Claude?
Sign up at cotlet.dev, log in to BrightLocal once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your BrightLocal account through Cotlet, in their phone apps too.
What can ChatGPT do in BrightLocal?
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in BrightLocal: check where you rank for your services; read your new reviews and draft replies; track a new service and run the report. You ask in plain words, and anything that reaches other people waits for your OK first.
Do I need the Grow plan?
For rankings, citations, locations and keyword changes, whatever plan you have in BrightLocal. Reviews need Reputation Manager, which BrightLocal sells in its Grow plan, and the 14-day trial includes it. Cotlet itself works in your own account. The Grow plan and Labs access are conditions of BrightLocal Anywhere, the official MCP server.
What can it not do yet?
The Local Search Grid and the Google Business Profile Audit need the location's Google Business Profile connected in BrightLocal. Without it list_local_search_grid_reports comes back empty and get_local_search_grid_report and get_gbp_audit answer null with a note. Reviews need Reputation Manager set up for the location, and a reply needs a connected Google Business Profile or Facebook page. Grids, audits, reviews, Active Sync alerts and Citation Builder campaigns were checked against BrightLocal's sample location or came back empty on our test account, and the reply was never posted. Not built: creating locations or reports, review request campaigns, the Google Business Profile post scheduler, buying citations, the Local Search Audit, and BrightLocal's billing and user settings.
Can my agent reply to every review?
No. respond_to_review posts a public reply to a Google or Facebook review, only when list_reviews shows can_reply true for it, which needs the Google Business Profile or Facebook page connected to Reputation Manager. Reviews on other sites such as Yelp can be read but not answered. The reply waits for your approval in the Cotlet console before it goes out.
Which tools change something in my account?
update_rank_tracker_keywords changes the keywords of your Rank Tracker report, up to 100 per report. rerun_report starts a manual run, and BrightLocal counts it against your ad-hoc run credits. respond_to_review publishes a reply to a customer. Only respond_to_review waits for your approval in the Cotlet console, because the reply reaches a customer; you can switch that wait off per tool. The three need write access for BrightLocal in the console, and the other 13 tools only read.
Does a re-run use up anything?
Yes. A manual run uses one of the ad-hoc run credits of your BrightLocal plan, and a Local Search Grid run also uses grid credits. After a trial ends BrightLocal stops runs. Scheduled runs are not affected and need no tool.
Why do new keywords show no position?
update_rank_tracker_keywords saves the keywords, and BrightLocal gives them positions on the next run. Call rerun_report with report_type rank_tracker to run it now; it takes a few minutes. A keyword outside the top 50 has a null rank.
How do I sign in to BrightLocal?
In your own Cloud Browser, on tools.brightlocal.com, with your email and password. Cotlet keeps that session alive between calls. If BrightLocal logs you out, your agent gets a link to sign in again.
Can I get a BrightLocal API key for my own business?
BrightLocal gives API keys through its support team (checked 23 Oct 2026). A Cotlet API key reaches your own BrightLocal login through the same tools as MCP, with no BrightLocal key needed.
Is the MCP server different from the REST API?
Only in how you call it. Both have the same 16 tools, inputs and answers, under one API key and one price. Agents use MCP; scripts, cron jobs and HTTP steps use REST.
What happens to my data if I leave?
Reset browser deletes your BrightLocal profile on our side, and closing your Cotlet account deletes the browser too. Unused credits stay valid for 12 months from purchase.
Is Cotlet affiliated with BrightLocal?
No. Cotlet is independent and not affiliated with BrightLocal.
Give your AI agents your signed-in browser.
Product: Integrations · How it works · Pricing · Security
Resources: Blog · API docs · Help center · Changelog · GitHub
Solutions: For developers · For automation agencies
Company: About · AI info: company facts · Contact
Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors
Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub
Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.