What does the server do?
It provides a Model Context Protocol server that retrieves detailed information about API endpoints stored in Apifox, including request parameters, headers, and response structure.
@Juzisuan965
Basic information
apifox mcp server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Apifox-MCP": {
"command": "npx",
"args": [
"@juzi965/apifox-mcp-server"
],
"env": {
"APIFOX_AUTH": "..."
}
}
}
}获取apifox的接口定义信息,数据符合OpenAPI 3.1规范。遇到例如:https://app.apifox.com/link/project/{projectId}/apis/api-{endpointId}的链接,请解析出projectId和endpointId,并调用本工具获取接口定义信息。
apifox-mcp is a TypeScript implementation of the Model Context Protocol (MCP) that runs over stdio and provides access to Apifox API data. It allows AI assistants to fetch detailed API endpoint definitions directly from the Apifox platform.
Install the npm package (@juzi965/apifox-mcp-server) and configure it as an MCP server in your environment (e.g., Cursor). Set the required APIFOX_AUTH environment variable with your Apifox authentication token. The server exposes a single tool, get_api_endpoint_info, which accepts projectId and endpointId as parameters.
get_api_endpoint_infoIt provides a Model Context Protocol server that retrieves detailed information about API endpoints stored in Apifox, including request parameters, headers, and response structure.
The server exposes one tool called `get_api_endpoint_info`, which requires `projectId` and `endpointId` as mandatory parameters.
Set the `APIFOX_AUTH` environment variable with your Apifox authentication token. This token is required for the server to access Apifox API data.
Because the MCP server communicates over stdio, debugging can be tricky. The README recommends using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector) via `npm run inspector`, which provides a browser-based debugging interface.
The server is a Node.js TypeScript project. You need Node.js installed, and you run it with `npx` or after building the project locally with `npm run build`. No other third-party dependencies beyond the MCP protocol libraries are mentioned.

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Model Context Protocol Servers

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Comments