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

Apidog MCP Server enables AI to connect and utilize API specifications within your Apidog project.

Configuring the MCP Client

Prerequisites

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

Any IDE that supports MCP:

Cursor

VSCode + Cline extension

Others

Obtaining API Access Token and Project ID

Generate API Access Token

Open Apidog, hover over your profile picture (top-right), and select Account Settings → API Access Token

Create a new API access token and replace <access-token> in the configuration below

Get Apidog Project ID

Open your target project in Apidog

Click "Project Settings" in the left sidebar, then copy the Project ID from "Basic Settings"

Replace <project-id> in the configuration below

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 following configuration in the opened mcp.json. Remember to replace <access-token> and <project-id> with your own:

macOS / Linux

Windows

{ "mcpServers": { "API specification": { "command": "npx", "args": [ "-y", "apidog-mcp-server@latest", "--project=<project-id>" ], "env": { "APIDOG_ACCESS_TOKEN": "<access-token>" } } } }

Verify Configuration

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

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

Successful connection is confirmed when AI returns your Apidog project's API information.

Important Notes

Replace <access-token> and <project-id> with your personal Apidog API access token and project ID.

If you need to work with API specification from several projects, simply add multiple MCP Server configurations to the configuration file. Each project should have its own unique <project-id>. For clarity, name each MCP Server following the format "xxx API Specification".

If your team syncs the MCP configuration file to a code repository, it is recommended to remove the line "APIDOG_ACCESS_TOKEN": "<access-token>" and instead, configure the APIDOG_ACCESS_TOKEN as an environment variable on each member's machine to prevent token leakage.

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": { "API specification": { "command": "npx", "args": [ "-y", "apidog-mcp-server@latest", "--project=<project-id>", // Required for on-premise deployment: "--apidog-api-base-url=<API address of the on-premise server, starting with http:// or https://>" ], "env": { "APIDOG_ACCESS_TOKEN": "<access-token>" } } } }

Connecting Other Data Resources to AI

Conntect Online API Documentation Published by Apidog 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": { "API specification": { "command": "cmd", "args": [ "/c", "npx", "-y", "apidog-mcp-server@latest", "--project=<project-id>" ], "env": { "APIDOG_ACCESS_TOKEN": "<access-token>" } } } }

Node.js Version Problems

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

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

Configuring the MCP Client#

Prerequisites#

Obtaining API Access Token and Project ID#

Configuring MCP in Cursor#

Important Notes#

Connecting Other Data Resources to AI#