Skip to main content
The Cognizo MCP server lets an AI client call the Cognizo API on your behalf — “how did Acme’s visibility move this week”, “which prompts are we losing”, “which domains cite our competitors but not us”. It’s a hosted, remote Model Context Protocol server, so there’s nothing to install.

Connect a client

Claude signs in; Cursor, VS Code, Windsurf and ChatGPT take a key.

Tools

All 62 tools: 58 API operations plus 4 workflow tools.

​
At a glance

​
How it works

The tool surface is generated from the same public OpenAPI spec that powers the API reference, so the tools and the endpoints never drift apart: one new public endpoint means one new tool, named after the same operation id. On top of that sit four workflow tools — hand-written shortcuts that chain several API calls into the answer a question actually needs, so the model doesn’t have to orchestrate three round-trips to say how a brand is doing.

​
Two ways to authenticate

Sign in — Claude’s web, desktop, mobile and Cowork clients can’t send a custom header, so they authorize in the browser instead. Cognizo is an official Claude connector, so you add it from the directory and pick which organization it reads. No key is ever created or pasted. API key — everything else, including Claude Code and ChatGPT, sends X-API-KEY. The organization comes from the key. Both end up in the same place: one organization’s data, the public surface only. Connect a client covers each.

​
What it can reach

Exactly what your credential can reach, and nothing more:
  • The public API surface — brands, topics, prompts, citations, competitors, ads, regions, opportunities and Content Studio.
  • Only brands your organization owns.
Anything outside that surface is rejected upstream with 403, the same as a direct API call. The MCP server has no privileges of its own — it is a proxy, not an account.
The server holds no credentials. Your key or token travels with each request from your client, is forwarded upstream, and is never persisted. See Security & troubleshooting.

​
Read and write

The generated tools cover writes as well as reads — creating brands, bulk-adding prompts, tracking competitors, soft-deleting topics. An assistant with your key can change your workspace, so treat MCP access like handing over dashboard access. If you want a read-only setup, issue a key you can revoke independently and keep an eye on what your client is allowed to call — most clients let you approve tools individually. Claude shows each tool’s read/write nature before you approve it; ChatGPT’s developer mode asks you to confirm write actions and shows the input it’s about to send.