Conntect Online API Documentation Published by Apidog to AI via Apidog MCP Server

Apidog MCP Server enables AI to connect and utilize online API documentation published by Apidog.

This configuration method only supports publicly published online documentation and does not support documentation with password or whitelist settings. For non-public documentations, it is recommended to use the project ID and personal API access token to read Apidog project data. For more details, refer to: Connecting API Documentation within Apidog Project to AI via Apidog.

Enabling MCP for Online Documentation

Apidog version should be ≥ 2.7.2.

Enable MCP Service

Navigate to Apidog project, then go to Share Docs → Publish Docs Sites → AI Features to enable MCP service.

Get Configuration File

After enabling, the Vibe Coding(via MCP) button will appear when accessing online documentation.

Clicking the button will display the configuration guide and the MCP config file, which automatically includes your documentation's site-id. Simply copy this configuration for IDE integration.

Configuring MCP Client

Prerequisites

Node.js environment installed (version ≥ 18, latest LTS recommended)

Any IDE that supports MCP:

Cursor

VSCode + Cline extension

Others

Copied MCP JSON configuration from Apidog online documentations

Configuring MCP in Cursor

Edit MCP Config File

Open Cursor editor, click the settings icon (top-right), select "MCP" from the left menu, then click "+ Add new global MCP server".

Add Configuration

Paste the MCP JSON configuration copied from online documentations into the opened mcp.json file:

macOS / Linux

Windows

{
  "mcpServers": {
    "apidog-site-123456": {
      "command": "npx",
      "args": [
        "-y",
        "apidog-mcp-server@latest",
        "--site-id=123456"
      ]
    }
  }
}

Verify Configuration

Test the connection by asking the AI (in Agent mode), for example:

Please fetch API documentation via MCP and tell me how many endpoints exist in the project.

If the AI returns correct API information, the connection is successful.

Important Notes

If you need to work with different API documentations, simply add multiple MCP Server configurations to the configuration file. Each API documentation should have its own unique <site-id>.

For users of the on-premise deployment, please include your on-premise server's API address in the IDE MCP configuration: "--apidog-api-base-url=<API address of the on-premise server, starting with http:// or https://>" Additionally, ensure network access to www.npmjs.com properly.

 {
  "mcpServers": {
    "apidog-site-123456": {
      "command": "npx",
      "args": [
        "-y",
        "apidog-mcp-server@latest",
        "--site-id=123456",
        // Required for on-premise deployment:
        "--apidog-api-base-url=<API address of the on-premise server>"
      ]
    }
  }
}

Connecting Other Data Resources to AI

Conntect API Specification within Apidog Project to AI via Apidog MCP Server

Conntect OpenAPI Files to AI via Apidog MCP Server

FAQs

Windows Configuration Issues

If standard configuration fails on Windows, use this instead:

{
  "mcpServers": {
    "apidog-site-123456": {
      "command": "cmd",
      "args": [
        "/c",
        "npx",
        "-y",
        "apidog-mcp-server@latest",
        "--site-id=123456"  // Replace with your Site ID
      ]
    }
  }
}

Node.js Version Problems

How to let AI reads the latest data from the updated API documentation?

Conntect Online API Documentation Published by Apidog to AI via Apidog MCP Server

Enabling MCP for Online Documentation#

Configuring MCP Client#

Prerequisites#

Configuring MCP in Cursor#

Important Notes#

Connecting Other Data Resources to AI#