Skip to content
Last updated

Model Context Protocol server

Model Context Protocol (MCP) is a standard that enables applications to provide context to large language models (LLMs). With MCP servers, AI assistants can retrieve additional information relevant to a user's query.

Realm provides built-in MCP server capabilities that expose your API Docs to AI assistants.

Benefits

  • Real-time API guidance — users receive accurate, contextual help about API endpoints and operations.
  • Secure API access — AI assistants can make authenticated requests to act on behalf of a user.
  • Dynamic documentation — AI assistants can extract and explain API reference content based on user needs.

Docs MCP server

Use the Docs MCP server to explore and discover APIs in your project. The server provides tools for browsing API definitions, exploring endpoints, and understanding API schemas.

Key features

  • Browse available APIs and their definitions.
  • Explore API endpoints and operations.
  • Access schema definitions and data models.
  • Navigate API paths and their details.

Connect an AI agent to the Docs MCP Server

After adding the option to the config file, the Docs is registered at your root URL under the /mcp path. For example: https://example.com/mcp.

Authentication

If your project requires login (rbac or requiresLogin configured), Docs MCP Server requires the user to authenticate using the configured method. This requirement ensures that AI Agents can only access APIs and operations the authenticated user has permission to view.

Available tools

Authentication tools

ToolParametersDescription
whoami-Returns information about the authenticated user.

API discovery tools

ToolParametersDescription
list-apisname?: stringLists available APIs with their context and purpose.
get-endpointsname: stringReturns all endpoints and their descriptions for a specific API.
get-endpoint-infoname: string
path: string
method: string		Returns comprehensive information about a specific endpoint, including parameters, security, and examples.
get-security-schemesname: string
path: string
method: string		Gets the security schemes for a specific API.
get-full-spec-documentname: stringReturns the complete OpenAPI definition for an API.

Search tools

ToolParametersDescription
searchquery: stringSearches documentation and returns relevant content for a query.

Connect an AI agent to the MCP server

The Docs MCP server is registered at your root URL under the /mcp path.

Use the MCP server

Users can connect their preferred AI tools that support MCP (for example, Cursor, Claude Code and VS Code) to your MCP server.

  1. Enable the MCP server in your configuration.
  2. Copy your MCP server URL and add it to your tool.

After connecting, the tool can access your OpenAPI documentation.

Connect Cursor to the MCP server

  1. In Cursor, open the command palette.
    • macOS: Command + Shift + P
    • Windows/Linux: Ctrl + Shift + P
  2. Type "Open MCP settings" in the command palette.
  3. Select "Add custom MCP".

Cursor opens the mcp.json file.

Configure the MCP server

  1. In mcp.json, add your server configuration:
{
  "mcpServers": {
    "example-mcp": {
      "url": "https://example.com/mcp"
    }
  }
}

Optionally, you can also pass additional headers that will be sent with each request:

{
  "mcpServers": {
    "example-mcp": {
      "url": "https://example.com/mcp",
      "headers": {
        "Authorization": "Basic MTIzOjEyMw=="
      }
    }
  }
}

  1. Save the mcp.json file.

  2. Return to MCP settings and confirm the connection. If authentication is required, select Needs login and complete the sign‑in flow. After connecting, Cursor displays the list of available tools.

Test the Cursor connection

In Cursor chat (Agent mode), ask a question that triggers an MCP tool.

Resources

 
Next page