|
| 1 | +--- |
| 2 | +title: "Model Context Protocol" |
| 3 | +description: "Generate MCP servers from your documentation or OpenAPI specs" |
| 4 | +icon: 'audio-waveform' |
| 5 | +--- |
| 6 | + |
| 7 | +## Overview |
| 8 | + |
| 9 | +The Model Context Protocol (MCP) is an open protocol that connects your functions to LLMs and AI applications. With Mintlify's integration, you can automatically generate an MCP server from your existing documentation or OpenAPI specifications, enabling seamless AI-powered interactions with your product. |
| 10 | + |
| 11 | +## Quick Usage Guide |
| 12 | + |
| 13 | +Any public documentation hosted on Mintlify can be extracted as an MCP server using a simple command: |
| 14 | + |
| 15 | +```bash |
| 16 | +npx @mintlify/mcp add <your-subdomain-or-domain> |
| 17 | +``` |
| 18 | + |
| 19 | +Examples: |
| 20 | + |
| 21 | +```bash |
| 22 | +# Using subdomain |
| 23 | +npx @mintlify/mcp add mintlify |
| 24 | + |
| 25 | +# Using domain |
| 26 | +npx @mintlify/mcp add mintlify.com |
| 27 | +``` |
| 28 | + |
| 29 | +### Authentication |
| 30 | + |
| 31 | +When you run the command, you'll need to provide two API keys, `External Admin Key` and `Chat API Key`. |
| 32 | + |
| 33 | +These can be found in your [Mintlify Dashboard](https://dashboard.mintlify.com/settings/organization/api-keys) under **Settings > API Keys**. |
| 34 | + |
| 35 | +<Frame> |
| 36 | + <img src="/images/mcp/mcp-terminal.png" alt="API Keys" /> |
| 37 | +</Frame> |
| 38 | + |
| 39 | +### Select MCP Clients |
| 40 | + |
| 41 | +After authentication, you'll choose which MCP clients to enable for your server: |
| 42 | + |
| 43 | +<Frame> |
| 44 | + <img src="/images/mcp/mcp-terminal-completed.png" alt="MCP Clients" /> |
| 45 | +</Frame> |
| 46 | + |
| 47 | +Once configured, your MCP server is ready to use with the command provided in the terminal. |
| 48 | + |
| 49 | +## Configuring Your MCP Server |
| 50 | + |
| 51 | +Now let's take a look at how to configure your MCP server. |
| 52 | + |
| 53 | +### Default Functionality |
| 54 | + |
| 55 | +All MCP servers include the `search` tool by default, allowing users to query information across your entire documentation. |
| 56 | + |
| 57 | +### Adding API Functions |
| 58 | + |
| 59 | +If you have an OpenAPI specification, you can expose specific endpoints as MCP tools by using the `x-mcp` extension at either the file or endpoint level. |
| 60 | + |
| 61 | +#### File-Level Configuration |
| 62 | + |
| 63 | +Enable MCP for all endpoints in a specification file: |
| 64 | + |
| 65 | +```json |
| 66 | +{ |
| 67 | + "openapi": "3.1.0", |
| 68 | + "x-mcp": { |
| 69 | + "enabled": true |
| 70 | + }, |
| 71 | + // Other OpenAPI content |
| 72 | +} |
| 73 | +``` |
| 74 | + |
| 75 | +#### Endpoint-Level Configuration |
| 76 | + |
| 77 | +Enable MCP for specific endpoints only: |
| 78 | + |
| 79 | +```json |
| 80 | +{ |
| 81 | + "paths": { |
| 82 | + "/api/v1/users": { |
| 83 | + "x-mcp": { |
| 84 | + "enabled": true |
| 85 | + }, |
| 86 | + // Endpoint configuration |
| 87 | + } |
| 88 | + } |
| 89 | +} |
| 90 | +``` |
| 91 | + |
| 92 | +### Authentication Handling |
| 93 | + |
| 94 | +If your OpenAPI spec defines authentication using securitySchemes, these authentication methods will be automatically applied to your MCP server. |
| 95 | + |
| 96 | +### Monitoring Your MCP Server |
| 97 | + |
| 98 | +After publishing your changes, you can view all available MCP tools in the **Available Tools** section on the MCP server page in your dashboard. |
| 99 | + |
| 100 | +<Frame> |
| 101 | + <img src="/images/mcp/mcp-server-page-light.png" alt="MCP Dashboard" class="block dark:hidden" /> |
| 102 | + <img src="/images/mcp/mcp-server-page-dark.png" alt="MCP Dashboard" class="hidden dark:block" /> |
| 103 | +</Frame> |
| 104 | + |
| 105 | +## Distribution |
| 106 | + |
| 107 | +### User Installation |
| 108 | + |
| 109 | +Your users can install and use your MCP server with: |
| 110 | + |
| 111 | +```bash |
| 112 | +npx @mintlify/mcp add <your-subdomain-or-domain> |
| 113 | +``` |
| 114 | + |
| 115 | +This provides them with a ready-to-use MCP server that connects your documented functions to AI applications. |
0 commit comments