Brand24 MCP Server
Mentions, tags, sentiment and cleanup in your Brand24 projects.
Hosted MCP Server
npx add-mcp 'https://cotlet.dev/mcp/v1/brand24'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
Brand24 API and MCP server: Let your AI agent clean up your Brand24 mentions.
Brand24 has an official MCP server and a REST API, and neither tags, deletes, blocks or re-scores a mention (checked 27 Oct 2026). The MCP server answers questions about events, stats, sources and topics on Pro and higher plans. Cotlet runs 10 Brand24 tools hosted, 4 of them writes, over MCP for agents and REST for scripts, on any plan.
Mentions, tags, sentiment and cleanup in your Brand24 projects. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.
- Free 7-day trial, no card
- Unofficial, not affiliated with Brand24
- Page: https://cotlet.dev/integrations/brand24-api-mcp-server
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by Brand24. Brand24 is a trademark of its owner. If Brand24's own integrations cover what you need, use them first.
What can you automate in Brand24?
- Delete junk mentions and block their sources
- Tag complaints, leads and questions
- Fix sentiment scored the wrong way
- Send weekly mentions, reach and sentiment
- Explain spikes from AI Events
- Add mentions Brand24 missed
Does Brand24 have an MCP server or an API?
- The official MCP server grants one OAuth scope, projects:read, and a review notes it "doesn't expose raw, mention-level search the way Brand24's dashboard does".
- The API has 26 read operations and one write, create_project. It is a paid add-on on Pro and Business and included on Enterprise; the key comes from your Customer Success Manager.
- Zapier says "Brand24 is not yet available on Zapier", and n8n and Make have no Brand24 app either.
| What you need | Brand24 MCP | Brand24 API | Cotlet |
|---|---|---|---|
| Stats, sentiment counts and AI events | Yes, as answers | Yes, as JSON | Yes |
| Read single mentions | No | On the product page, not in the spec | Yes, as the Mentions tab shows them |
| Tag mentions or change sentiment | No | No | Yes |
| Delete, block or add mentions | No | No | Yes, deletes after your OK |
| Plan needed | Pro and up | Paid add-on, or Enterprise | Any plan, trial too |
Checked 27 Oct 2026. Sources: Brand24 MCP (Brand24 Help), Brand24 API Data spec (OpenAPI), Brand24 Social Listening API, API integration (Brand24 Help), Brand24 pricing, Brand24 on Zapier
How does Cotlet connect to Brand24?
- Sign in to Brand24. Use your own account in its Cotlet Cloud Browser.
- Choose MCP or REST. Connect your agent or create a Cotlet API key.
- Run your workflow. Ask your agent or send an HTTP request.
We never keep your Brand24 password, and no mention is deleted or tagged before you approve it.
Connect Brand24 to your agent or workflow
Use MCP with your AI agent, or HTTP requests in n8n, Make, Zapier and scripts. Follow the MCP setup below or jump to the REST guide.
- Sign in to Brand24 in a Cloud Browser. Create a Cotlet account, open Brand24 in its Cloud Browser, sign in with your own Brand24 login on any plan, trial included, and press Enable for agents.
- Add the Cotlet address. Put https://cotlet.dev/mcp/v1 into your agent's MCP server or connector settings.
- Allow the connection. Chat apps open a Cotlet sign-in page. Code editors, n8n and scripts use an API key from the console instead.
https://cotlet.dev/mcp/v1 is the one address for all your Cotlet apps, Brand24 among them. It sits next to Brand24's own connector without a clash: keep that one for summaries and topics. If you enable Brand24 after connecting, refresh the connector so its tools appear.
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 \
--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",
"headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
}
}
}
Codex:
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
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: brand24_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: brand24_write
How to use the Brand24 REST API
Create your Cotlet API key
Create a Cotlet API key with access to Brand24 and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.
Connect Brand24 in Cotlet and enable it for agents. Account access: Your own Brand24 account (email and password or Google sign-in) with access to the project. What your agent can do follows your account and plan.
Make your first Brand24 API request
REST:
curl https://cotlet.dev/api/v1/brand24/projects \
-H "Authorization: Bearer $COTLET_API_KEY"
Read projects and apply the operation limits
A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.
Illustrative response excerpt:
{
"status": "success",
"app": "brand24",
"tool": "list_projects",
"result": {
"projects": [
{
"project_id": 123456789,
"name": "Northwind Coffee"
},
{
"project_id": 234567891,
"name": "Competitor Roast Lab"
}
]
}
}
Returns the ID and name of every project you can open. Run it first: the other tools take a project_id.
It changes nothing in Brand24.
Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.
Brand24 workflows for agents and automations
| Tool | Connect through | Example workflow |
|---|---|---|
| n8n | HTTP Request | Returns mentions, reach and sentiment of a project for a date range. Use get_project_stats in your configured marketing report. |
| Make | HTTP > Make a request | Lists the mentions of a project as the Mentions tab shows them. Use list_mentions in your configured marketing report. |
| Python or Node.js | REST API | Lists the AI Events of a project, the explained spikes in mentions or reach. Use list_events in your configured marketing report. |
Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.
Cotlet reads Brand24; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.
Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.
The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.
Brand24 API endpoints and MCP tools
Mentions, tags and sentiment
Tags and sentiment change only your project's view; the author of a mention never sees them. Facebook, Instagram and X mentions come with the text Brand24 is allowed to show.
- List mentions (
list_mentions, read): Lists the mentions of a project as the Mentions tab shows them. - List tags (
list_tags, read): Lists the tags you can put on mentions in a project. - Tag mentions (
tag_mentions, write, asks first): Puts one tag on one or more mentions. - Set mention sentiment (
set_mention_sentiment, write): Sets the sentiment of one or more mentions. - Add mention (
add_mention, write): Adds a public mention to a project by hand, as the Add mentions manually form does.
Cleanup and blocked sources
A block holds for one project. Run the cleanup per project, or name the projects in the prompt.
- List excluded sources (
list_excluded_sources, read): Lists the domains and social media authors a project no longer collects from. - Delete mentions (
delete_mentions, write, asks first): Deletes mentions from a project, and can block their source or mark them as spam.
Projects, stats and AI events
AI Events start on Pro. On Individual and Team, list_events returns an empty list.
- List projects (
list_projects, read): Lists the monitoring projects of your Brand24 account. - Get project stats (
get_project_stats, read): Returns mentions, reach and sentiment of a project for a date range. - List AI events (
list_events, read): Lists the AI Events of a project, the explained spikes in mentions or reach.
Inputs, REST path and example response of every tool: https://cotlet.dev/integrations/brand24-api-mcp-server#tools
Who can see my Brand24 session, and how do I revoke it?
- What we store. Your signed-in Brand24 profile, encrypted with AES-256-GCM, in Finland. Never the password.
- What your agent gets. 10 Brand24 tools. No cookie and no login.
- What the session sees. The projects your Brand24 user can open, with your plan's limits.
- What no tool touches. Billing, keywords, alerts, team members and project settings.
- If Brand24 signs you out. We email you a sign-in link. You sign in yourself, we never do.
- How to cut access. Disable for agents, reset the browser or delete the key. The next call fails.
Your agent reads mentions of other people's public posts, so treat what it pulls the way you treat a Brand24 export. The Cotlet site has A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results).
Approvals, undo and mistakes
- Reads the blocks. The project's excluded domains and authors, so it proposes no block twice.
- Sorts the new mentions. Junk to delete, repeat sources to block, unclear ones left for you with a reason.
- Waits for your OK. One delete call per verdict waits in your Cotlet console, with the IDs and titles.
- Checks and reports. Reads the window again, then lists what went and what the project now ignores.
| Action | Undo |
|---|---|
| Delete a mention | No restore is documented |
| Delete and block the source | Project settings, Sources tab, delete filter; the mention stays gone |
| Report as SPAM | No undo is documented |
| Tag mentions | No tag removal is documented |
| Change sentiment | Set the old value back |
| Add a mention by hand | delete_mentions removes it |
2 of the 4 write tools ask first: delete_mentions and tag_mentions, because neither has a documented way back. set_mention_sentiment and add_mention run at once, since a second call reverses them and nobody outside your team sees either. Reads run at once. For a scheduled run you can switch the wait off per tool.
Deleted mentions drop out of the charts and PDF reports. Run the cleanup before you export a client report, not after.
MCP call:
{
"name": "tag_mentions",
"arguments": {
"project_id": 123456789,
"mention_ids": [
"7001234520",
"7001234521",
"7001234522"
],
"tag": "Complaint"
}
}
REST:
curl -X POST https://cotlet.dev/api/v1/brand24/projects/123456789/mentions/tag \
-H "Authorization: Bearer $COTLET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"mention_ids":["7001234520","7001234521","7001234522"],"tag":"Complaint"}'
Response:
{
"tagged": 3,
"tag": "Complaint",
"tag_created": false
}
A cron job or your own dashboard can call the same tools over REST at /api/v1/brand24, with one key and one price and no API add-on on the Brand24 side. A call your Brand24 user is not allowed to make returns an error and costs nothing. Every tool row above lists its REST path.
How much does the Brand24 MCP server cost?
About $31 a month for a brand project and a competitor project, 5,340 credits. Works on Brand24 Individual, $199 a month billed yearly, with no API add-on.
| Job | Calls | Credits |
|---|---|---|
| Delete junk mentions and block sources, daily | 6 × 30 | 1,800 |
| Tag complaints and sales leads, daily | 5 × 30 | 1,500 |
| Fix wrong sentiment, weekly | 5 × 4 | 200 |
| Report for 2 projects, weekly | 7 × 4 | 280 |
| Add mentions Brand24 missed | 3 × 2 | 60 |
| Cloud Browser, 30 days | 1,500 | |
| Total | 5,340 |
- Free 7-day trial, no card
- 10 credits per successful call, MCP or REST
- 50 credits a day for the Cloud Browser
- No Brand24 Pro plan or API add-on needed
The month is our example: about 300 new mentions a week in the brand project, a daily cleanup and tagging run, a weekly sentiment fix and a Monday report for both projects. Brand24 publishes no typical size; Individual allows 2,000 mentions a month and Team 10,000. Dollars at the $29 pack rate.
Brand24 MCP server: official connector, API or hosted
| Option | What it does | Where it stops |
|---|---|---|
| Brand24 MCP | Official server at mcp.brand24.com with 4 read tools: account events, project stats, sources and topics. Also a ChatGPT app. | Answers only, no mention list. Pro and up. |
| Brand24 API | REST with 26 reads (stats, AI summary, insights, topics, tags) and create_project. | Paid add-on, key from your Customer Success Manager. Changes no mention. |
| korniichuk/brand24-api | A Python Selenium script for the Brand24 panel. 12 stars, last push 22 Apr 2019. | Built for the 2019 panel, no MCP, nobody maintains it. |
| GitHub, Zapier, n8n | No Brand24 MCP server on GitHub or in the MCP Registry, and no Brand24 app on Zapier, Make or n8n (27 Oct 2026). | Only generic HTTP calls against the paid API. |
If you are on Pro or higher and want answers about spikes, topics and sources, Brand24's own connector comes with your plan; use it. If you feed a dashboard, the API add-on fits. When the agent should delete junk, block sources, tag mentions or fix sentiment, or you are on Individual or Team, that is the part Cotlet covers.
Who runs Cotlet
Take Group sp. z o.o. runs Cotlet: a software company registered in Poland, EU (VAT PL6342984273), in business since 2019. The 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 Brand24 tools.
Brand24 API and MCP: questions
How do I get access?
Sign up free at https://cotlet.dev, open Brand24 under Integrations in the console and sign in to Brand24 in its Cloud Browser. The trial begins when you sign up and needs no card.
How do I connect Brand24 to ChatGPT or Claude?
Sign up at cotlet.dev, log in to Brand24 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 Brand24 account through Cotlet, in their phone apps too.
What can ChatGPT do in Brand24?
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Brand24: clean up irrelevant mentions; tag complaints and sales leads; correct wrong sentiment. You ask in plain words, and anything that reaches other people waits for your OK first.
Does it show Facebook, Instagram and X mentions in full?
list_mentions returns what the Mentions tab shows. Brand24 limits exported data from Twitter, Facebook and Instagram because their privacy policies do not allow exports, and its API returns empty text fields for them.
Can my agent create a project or change its keywords?
Not built. Project creation, with keywords, required and excluded words and a language filter, exists in the official Brand24 API.
Can I use Brand24's own MCP server and Cotlet together?
Yes. They are two connectors in the same agent. Brand24's answers questions about events, topics and sources on Pro and up; Cotlet lists single mentions and makes the changes. Your agent picks the tool by name.
Does it work on Individual and Team?
Yes. Brand24's pricing table lists mention tagging and AI sentiment on every plan, and the tools work in the Mentions tab you already have. Only list_events needs Pro or higher, where AI Events detection starts.
Is the MCP server different from the REST API?
Only in how you call it. Both have the same 10 tools, inputs and answers, with one API key and one price. Agents use MCP; scripts and dashboards use REST.
Is Cotlet affiliated with Brand24?
No. Cotlet is independent and not affiliated with Brand24 Global Inc.
Can I use the Brand24 API without an AI agent?
Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.
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.