Jesse MCP — connect in Cursor

Keep Jesse running and open its dashboard. The connection guide shows where to find the ready-made setup for your assistant.

Register Jesse in Cursor

Copy the configuration from the dashboard (recommended)

1. In the Jesse dashboard, open More options (⋮) at the bottom of the sidebar, click AI Assistants, and choose Cursor.
2. Click Copy mcp.json and paste it into your user-level ~/.cursor/mcp.json. If the file already lists servers, add only the jesse entry inside mcpServers.
3. Restart Cursor if it does not pick up the new server right away.

The copied configuration already contains your MCP address and token (see the note about plain-text storage below).

Manual setup

For this manual alternative, copy your token from AI Assistants → Manual connection details. See Manual authentication for terminal-based setup.

Exact labels change as Cursor updates, but the flow is usually:

1. Open Settings and find MCP, Tools & MCP, or similar.
2. Add a server (or equivalent) and paste the address Jesse printed in the terminal. It ends with /mcp and is http://localhost:9000/mcp by default, or <DASHBOARD_URL>/mcp when Jesse runs on another machine (for example http://192.168.1.20:9000/mcp).
3. Under HTTP headers, add a header named Authorization with the value Bearer <your MCP token>. Jesse uses a static token, not OAuth; do not use an OAuth or “Authenticate” option for Jesse.
4. Save, then restart Cursor if it does not pick up the new server right away.

The equivalent entry in Cursor’s mcp.json is:

{
  "mcpServers": {
    "jesse": {
      "url": "http://localhost:9000/mcp",
      "headers": {
        "Authorization": "Bearer <your MCP token>"
      }
    }
  }
}

Cursor stores the header value in plain text. Prefer your user-level ~/.cursor/mcp.json over a project .cursor/mcp.json, and never commit a file that contains the token.

If something fails, turn on MCP_LOG_IN_TERMINAL in .env while you debug—see Environment variables for MCP.

Agent rules (optional but recommended)

Jesse automatically writes and maintains AGENTS.md at the project root every time you run jesse run, so Cursor can read the rules without you pasting anything when it works in that project folder. See MCP agent rules for details on what's in the file, how the auto-sync works, how to add your own notes without losing them on upgrade, and what to do when Cursor runs on another computer.

• MCP in Cursor
• MCP integrations (help)

Same machine, same network story

If Cursor runs on Windows and Jesse runs inside WSL (or the other way around), localhost can refer to different machines. If you see connection errors, check Cursor’s docs for WSL or remote MCP setup, or run Jesse and Cursor in the same environment so they share one loopback network.