Your workspace, inside the assistant you already use

The terminal client. One command adds the server; the first tool call walks you through sign-in in a browser.

What you need: Nothing to paste. Step 2 signs you in and stores a scoped token for you — a bearer token is only for CI, and the note below says how.

1. 1

   Add the server. No credential goes in this command.

   bash

   claude mcp add --transport http atrix https://atrix.dev/api/mcp

2. 2

   Run /mcp inside Claude Code and choose Authenticate. A browser opens, you pick the workspace and the scopes, and the token is stored for you.

   text

   /mcp

3. 3

   Check it took.

   bash

   claude mcp list

A first connection asks only to read (customers, products, work, ideas). Tools that change things are listed as needing additional approval; the first time one is called, Claude Code is told which scope is missing and re-opens the browser to approve exactly that. To widen or change a connection yourself, run /mcp, choose atrix, and Authenticate again. Prefer a token you control? Skip the browser entirely with --header "Authorization: Bearer atx_pat_…".

Add Atrix as a custom connector. There is nothing to install and nothing to paste but the URL — the sign-in happens in the app.

What you need: Nothing to paste but the URL. Claude signs you in and registers itself.

1. 1

   Open Settings → Connectors → Add custom connector.

2. 2

   Paste the endpoint and save.

   text

   https://atrix.dev/api/mcp

3. 3

   Click Connect. You will be asked which workspace, and which of the scopes below to grant. Approve, and the tools appear in the composer.

Claude registers itself automatically — there is no client ID to create and no secret to store.

Atrix ships the search and fetch tools ChatGPT's connectors and Deep Research require, so your workspace is searchable the same way the web is.

What you need: Nothing to paste but the URL. ChatGPT signs you in when you connect.

1. 1

   Open Settings → Connectors → Create, and choose an MCP server.

2. 2

   Paste the endpoint.

   text

   https://atrix.dev/api/mcp

3. 3

   Sign in when prompted, and pick the scopes. Deep Research will then search pages, products, ideas and work items, and fetch any result in full.

search matches page bodies, not just titles — which is what you want, given how many pages are called Untitled.

Two commands: one to add the server, one to sign in.

What you need: Nothing in the config file. The second command signs you in; a bearer token is only for CI, as below.

1. 1

   Add it. No credential goes in this command.

   bash

   codex mcp add atrix --url https://atrix.dev/api/mcp

2. 2

   Sign in.

   bash

   codex mcp login atrix

3. 3

   Confirm.

   bash

   codex mcp list

For CI, where no browser exists: codex mcp add atrix --url … --bearer-token-env-var ATRIX_TOKEN.

Any client that speaks Streamable HTTP works. Most of them take the same JSON.

What you need: Either — OAuth if the client can open a browser, a token if it cannot. Both shapes are below.

1. 1

   Add Atrix to the client's MCP config — .cursor/mcp.json for Cursor, and the same shape almost everywhere else.

   json

   {
     "mcpServers": {
       "atrix": {
         "url": "https://atrix.dev/api/mcp"
       }
     }
   }

2. 2

   If the client cannot do OAuth, hand it a token instead.

   json

   {
     "mcpServers": {
       "atrix": {
         "url": "https://atrix.dev/api/mcp",
         "headers": { "Authorization": "Bearer atx_pat_…" }
       }
     }
   }

It is an HTTP endpoint speaking JSON-RPC. No SDK required, though the official MCP SDKs work unchanged.

What you need: This is the one that needs a token. Create one in settings, and export it as ATRIX_TOKEN.

1. 1

   List what your token may call.

   bash

   curl -s https://atrix.dev/api/mcp \
     -H "Authorization: Bearer $ATRIX_TOKEN" \
     -H "Content-Type: application/json" \
     -H "Accept: application/json, text/event-stream" \
     -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

2. 2

   Call one.

   bash

   curl -s https://atrix.dev/api/mcp \
     -H "Authorization: Bearer $ATRIX_TOKEN" \
     -H "Content-Type: application/json" \
     -H "Accept: application/json, text/event-stream" \
     -d '{"jsonrpc":"2.0","id":2,"method":"tools/call",
          "params":{"name":"search","arguments":{"query":"pricing"}}}'

The transport is stateless, so there is no session to keep alive and no ordering to preserve. Every request stands alone.