Use your Chat.co experts in Cursor

1. Availability

The Chat.co listing on cursor.directory is a community directory entry, separate from Cursor's official marketplace. We have applied to the official marketplace; Cursor's decision has not been confirmed.

In Cursor we have verified OAuth sign-in and discovery of all four tools. The complete flow of asking an expert and opening its sources has not yet been independently verified inside Cursor. It uses the same server as the hosts where it has been.

2. Before you start

• Your own Chat.co account. You sign in yourself during setup. Never use another person's login.
• A workspace with at least one expert you can chat with in Chat.co, on an active plan. If someone else manages the account, they give you access to experts; see Team, roles & seats.
• Message credits in that workspace for expert answers and standalone searches. Listing experts and opening sources are free.
• Optional: permission to search an expert's knowledge directly. You only need it for standalone search. Asking questions and opening an answer's citations do not require it.
• Cursor installed and signed in, with access to Agent chat.

3. Add Chat.co to Cursor

Option A: from cursor.directory

1. 1

   Open the listing

   Go to cursor.directory/plugins/chatco-experts and select Add to Cursor.

2. 2

   Check the server in Cursor

   Cursor opens with the server to install. Check that it points at https://mcp.chat.co/mcp and contains no credentials, then install it.

Option B: edit mcp.json

Cursor reads MCP servers from .cursor/mcp.json in a project, or from ~/.cursor/mcp.json for every project. Remote servers need only a url. Add a chatco entry inside your existing mcpServers object rather than replacing the file:

{
  "mcpServers": {
    "chatco": {
      "url": "https://mcp.chat.co/mcp"
    }
  }
}

Sign in

1. 1

   Open Cursor’s MCP settings

   In current versions this is the Customize panel in the sidebar. Find chatco in the MCP servers list.

2. 2

   Connect

   Select the connect or login action next to chatco. Your browser opens the Chat.co approval page. After you approve, Cursor lists four tools: list_authorized_experts, consult_expert, search and fetch.

4. Approve in Chat.co

Every host sends you to the same Chat.co approval page. Sign in if asked, then check each part before you approve:

Choose Approve connection to finish, or Cancel to stop. The only permission requested is chatco:read. It means the app cannot change your chatbots, knowledge, settings or account. It does not make the connection free of side effects: asking an expert saves the conversation in Chat.co and uses message credits, and a standalone search uses credits too, exactly as in the Chat.co app. Your questions, and the answers, excerpts and files you are permitted to receive, pass to the AI app and its provider.

5. Your first cited answer

Run these in Cursor’s Agent chat. HR Handbook is a made-up example; use the name of one of your own experts.

1. 1

   Discover your experts

   prompt

   Copy

   Which Chat.co experts can I ask?

   Expect: the experts in the workspace you approved, with short descriptions, and whether you can search each one's documents directly. Free.

2. 2

   Ask a question and request citations

   prompt

   Copy

   Ask the HR Handbook expert how many vacation days a new employee gets. Cite the sources.

   Expect: the expert's answer with citations that link to supporting documents. It is charged once, at the expert's normal Chat.co rate. Expert answers can take longer than an ordinary chat reply; while it waits, the app may check back on the same question several times, and you are still charged once. Answers do not include credit-cost notes; your usage appears in Chat.co.

3. 3

   Follow up in the same conversation

   prompt

   Copy

   Does that change after two years of service?

   Expect: an answer that builds on the previous one, because the app continues the same expert conversation. If the reply ignores the earlier context, ask the app to continue the same Chat.co conversation.

4. 4

   Open a source

   prompt

   Copy

   Open the source for the first citation.

   Expect: the cited passage in the conversation, or a link to a Chat.co supporting-document page. Private documents ask you to sign in with the account that received the answer. Opening sources is free, even when credits have run out.

5. 5

   Optional: search documents directly

   prompt

   Copy

   Search the HR Handbook expert's documents for "parental leave".

   Expect: a list of matching sources you can open. This works only for experts marked as directly searchable. Each completed search costs 0.5 message credit, even when nothing matches.

6. Message credits

A search that completes with no matches still counts. Failed operations, inaccessible experts and retries of the same operation are not charged again. Your existing allocation applies; there is no checkout inside the connector. When credits run out, new paid requests stop, but you can still list experts and open sources you already received.

7. Common errors

8. Disconnect

1. 1

   Revoke access in Chat.co

   Open Connected applications in Chat.co, find the app and workspace, and choose Disconnect. The app loses access to the connector from its next request.

2. 2

   Remove the server from the app

   In Cursor's MCP settings, turn chatco off or delete it. Or remove the chatco entry from mcp.json.

Disconnecting stops future access. It cannot remove answers or excerpts the app already received; that app's own terms and privacy policy govern them. To reconnect, start again from the app.

9. For developers & agents

You don't need this section to use Chat.co from an AI app. It documents the protocol for developers and for agents that call the tools directly.

Server

Tools

* Required.

Recipe for agents

1. 1

   List experts first

   Call list_authorized_experts. Only use id values it returns. Offer search only for experts whose access.knowledgeSearch is true.

2. 2

   Consult with a fresh operation_id

   Generate a new identifier (a UUID works) for each new question. Keep the returned conversation_id.

   consult_expert argumentsjson

   Copy

   {
     "expert_id": "<id from list_authorized_experts>",
     "question": "How many vacation days does a new employee get? Cite the sources.",
     "operation_id": "7f3b2c1e-5a9d-4e6f-8b0a-2d4c6e8f1a3b"
   }

   result (abridged)json

   Copy

   {
     "conversation_id": "<keep for follow-ups>",
     "answer": "New employees receive … [1]",
     "citations": [
       {
         "id": "<source id>",
         "title": "Employee handbook",
         "url": "<source link>"
       }
     ]
   }

3. 3

   Follow up in the same conversation

   Pass the conversation_id back with a new operation_id.

   consult_expert argumentsjson

   Copy

   {
     "expert_id": "<same expert>",
     "conversation_id": "<conversation_id from the first answer>",
     "question": "Does that change after two years of service?",
     "operation_id": "c41e9d27-0b6a-4f38-9e15-7a2d8c3b6f90"
   }

4. 4

   Read evidence with fetch

   Pass the citation's id and its title. The title is shown in approval prompts; the id is the lookup key. The excerpt may not be the whole document.

   fetch argumentsjson

   Copy

   {
     "id": "<source id from the citation>",
     "title": "Employee handbook"
   }

5. 5

   Present the answer with its links

   Show every cited source as a link to its url. Offer entries under files as downloads, not as citations. Don't add credit rates, model names or internal configuration to the answer.

Synthetic example: the HR Handbook expert, its answer and the angle-bracket values are placeholders. Use the identifiers and source links the server actually returns.

10. References

• Chat.co experts in your AI apps — overview, status of every host, credits and privacy
• Connected applications — review or disconnect
• Chat.co on cursor.directory (community listing)
• Cursor: Model Context Protocol (MCP)
• Chat.co experts package on GitHub
• Support: support@chat.co