Hazelchat

npx add-mcp 'https://app.hazelchat.co/mcp'

Work on your agent from Claude, ChatGPT or Claude Code

Check and improve your agent from Claude, ChatGPT or Claude Code. An assistant you connect can read your agent's activity, ask test questions against your saved draft and add answers to your draft. Publishing stays in the Hazelchat console.

Connect an assistant

The connection address is https://app.hazelchat.co/mcp. It is a remote MCP server: your assistant signs in to Hazelchat with your own account, you choose what it may do, and each connection works with one workspace. You can disconnect it at any time under Settings, AI assistants.

• Claude (claude.ai and the desktop app)

  Open Customize, then Connectors, choose + Add and then Add custom connector. Name it Hazelchat, paste the address and choose Continue. Claude opens Hazelchat so you can choose what it may do. On Team and Enterprise plans an Owner adds connectors first; on the Free plan Claude allows one custom connector. These steps follow Claude's help page.

• ChatGPT (on the web)

  Open Plugins, select the plus button and then Add custom MCP server. Enter Hazelchat as the name, paste the address, choose OAuth, confirm the notice and select Create as a plugin. Your ChatGPT plan and workspace settings decide whether you can add your own servers and use tools that change anything. These steps follow OpenAI's guide.

• Claude Code

  Run claude mcp add --transport http hazelchat https://app.hazelchat.co/mcp, then /mcp in Claude Code to sign in. For tools that cannot sign in, create a key under Settings, AI assistants, and add --header "Authorization: Bearer <your key>". Keys are shown once; up to five per workspace.

Connecting only works in the assistant's own browser tab. A sign-in request is valid for ten minutes and can be answered once. Hazelchat is not listed in Claude's or ChatGPT's directories yet, so add it with the address above.

This page is about your own assistant working on your workspace. For the public address your customers' AI agents use to ask your agent questions, see AI agents.

What an assistant can do

• Agent overview

  The published version, whether it is live, its websites, this period's answer allowance, test answers left today, and counts for the last 7 and 30 days: conversations, questions, answered from sources, handed over, enquiries, confirmed bookings. Counts only.

• Unanswered questions

  Questions visitors asked that the agent had no source for, newest first. Requests for a person are not included. Email addresses and phone numbers are removed.

• Search conversations

  Visitor questions matching a keyword and how the agent answered each one. Contact details are removed before matching, so they cannot be searched for.

• Recent enquiries

  Enquiries from the last 30 days with how the agent answered the last question. Names, email addresses and messages as written only when you allowed contact details for that connection and visitor details are on in Hazelchat.

• Ask a test question

  Asks the agent a question against your saved draft, like Test agent in the console, and returns the answer with the sources it quoted. Each question uses one of your 50 test answers a day. Nothing is shown to visitors.

• Add an answer to the draft

  Adds a Text snippet or a Q&A to your draft, marked as added via AI assistant. Visitors see it only after you review and publish the draft in the console.

Claude and ChatGPT ask you before they run the last two tools: a test question uses one of your test answers, and an added answer goes to your draft only. Your visitors never see it until you publish.

An assistant cannot publish, switch your agent on or off, change settings, websites or billing, edit or delete sources, or read anything outside the workspace it is connected to. Publication review marks every change that came through an assistant.

Permissions you choose

• Read activity

  The overview, unanswered questions, conversations and enquiries, without contact details.

• Ask test questions

  Each one uses one of your 50 test answers a day.

• Add answers to your draft

  Nothing goes live until you publish in the console.

• See enquiry contact details

  Names, email addresses and messages as written, when visitor details are on. Off unless you choose it.

Limits and errors

Each connection may make 60 requests a minute, and a workspace 120 a minute. Test questions are limited to 10 a minute per connection on top of the daily cap. Over a limit, requests answer 429 with a Retry-After header. A connection answers 403 while its workspace is not on a paid plan; signing in again is not needed once the plan is paid again. Requests without a valid sign-in or key answer 401 with the metadata address assistants use to start signing in. If you left a permission off when connecting, the tools that need it say so, and your assistant can ask you to connect again with it.

For developers: the server speaks the Model Context Protocol over HTTP at the address above, with OAuth 2.1 (authorization code with PKCE, client metadata documents and dynamic client registration) and the metadata documents under /.well-known/oauth-protected-resource/mcp and /.well-known/oauth-authorization-server. Owner API keys for the enquiry API do not work here, and assistant keys do not work there. A missing permission is an OAuth step-up (insufficient_scope).

Support

Questions about connecting an assistant, or something not working: email hello@hazelchat.co with the name of your assistant. To report a security problem, use the same address with "Security" in the subject.