Cursor Integration

Cursor is an AI-powered code editor with MCP support. This guide shows how to connect RLM to Cursor for documentation-aware coding assistance.

Prerequisites

• Cursor version 0.40 or later (MCP support required)
• An RLM project with at least one document indexed
• An API key from your RLM dashboard

Setup

Step 1: Open MCP Settings

In Cursor, go to Settings → Features → MCP Servers.

Step 2: Add Configuration

Click Edit Config and add the following to your mcp_config.json:

{

  "mcpServers": {

    "rlm-docs": {

      "command": "npx",

      "args": [

        "-y",

        "@anthropic-ai/mcp-proxy",

        "https://your-app.com/api/mcp/PROJECT_ID"

      ],

      "env": {

        "MCP_API_KEY": "YOUR_API_KEY"

      }

    }

  }

}

Step 3: Enable the Server

After saving the configuration:

1. Return to the MCP Servers settings
2. Find "rlm-docs" in the list
3. Toggle it ON
4. Wait for the connection indicator to turn green

Using RLM in Cursor

Once connected, you can use RLM tools in Cursor's AI chat (Cmd/Ctrl + L):

How does the authentication system work in this project?

[Using rlm_ask]

Based on your documentation, the auth system uses JWT...

Composer Mode

RLM works great with Cursor's Composer mode (Cmd/Ctrl + I). When editing code, Cursor will automatically query your documentation for context.

Alternative: Direct HTTP (Experimental)

If Cursor supports direct HTTP MCP servers in your version, you can use this simpler configuration:

{

  "mcpServers": {

    "rlm-docs": {

      "transport": "http",

      "url": "https://your-app.com/api/mcp/PROJECT_ID",

      "headers": {

        "X-API-Key": "YOUR_API_KEY"

      }

    }

  }

}

Troubleshooting

Next Steps