by apifox
Apifox MCP Server enables Apifox integration by connecting AI coding assistants to API definitions, allowing natural-lan
Connects Apifox API documentation to AI coding assistants like Cursor and Cline, allowing developers to generate and modify code based on API specifications using natural language commands.
Apifox MCP Server is an official MCP server published by apifox that provides AI assistants with tools and capabilities via the Model Context Protocol. Apifox MCP Server enables Apifox integration by connecting AI coding assistants to API definitions, allowing natural-lan It is categorized under developer tools.
You can install Apifox MCP Server in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Apifox MCP Server is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
I recommend Apifox MCP Server for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Apifox MCP Server reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Apifox MCP Server has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Apifox MCP Server is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Useful MCP listing: Apifox MCP Server is the kind of server we cite when onboarding engineers to host + tool permissions.
According to our notes, Apifox MCP Server benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Apifox MCP Server has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Strong directory entry: Apifox MCP Server surfaces stars and publisher context so we could sanity-check maintenance before adopting.
I recommend Apifox MCP Server for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Useful MCP listing: Apifox MCP Server is the kind of server we cite when onboarding engineers to host + tool permissions.
showing 1-10 of 48
使用 Apifox MCP Server,可以将 Apifox 项目内的接口文档作为数据源提供给 Cursor 等支持 AI 编程的 IDE 工具以便让 AI 能够直接访问项目对应的接口文档数据。
开发者可以通过 AI 助手完成以下工作:根据接口文档生成或修改代码、搜索接口文档内容等等,至于通过这个接口文档数据能让 AI 干什么更多更强大的活,请发挥你和你们团队的想象力😜
安装配置好 MCP 后,Apifox MCP Server 会自动读取 Apifox 整个项目里的所有接口文档的数据并缓存在本地电脑,AI 可以通过 MCP 读取项目内所有的接口的接口文档数据。
你只要告诉 AI 你想要通过 API 文档做什么即可,示例:
注意:接口文档数据默认是会缓存在本地的,如果 Apifox 内的数据有更新,请告诉 AI 刷新接口文档数据,否则 AI 读到的数据可能不是最新的。
<access-token><project-id>将下面 JSON 配置添加到 IDE 对应的 MCP 配置文件里:
{
"mcpServers": {
"API 文档": {
"command": "npx",
"args": [
"-y",
"apifox-mcp-server@latest",
"--project-id=<project-id>"
],
"env": {
"APIFOX_ACCESS_TOKEN": "<access-token>"
}
}
}
}
如果使用 Windows 操作系统,而上文的配置文件无法正常工作,请使用如下配置文件:
{
"mcpServers": {
"API 文档": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"apifox-mcp-server@latest",
"--project-id=<project-id>"
],
"env": {
"APIFOX_ACCESS_TOKEN": "<access-token>"
}
}
}
}
~/.cursor/mcp.json 或项目内的 .cursor/mcp.json注意:
<access-token> 和 <project-id> 替换为你个人的 Apifox API 访问令牌和 Apifox 项目 ID。<project-id>), MCP Server 的名字填写“xxx API 文档”。<access-token>",改成每个成员在自己电脑里配置名为 APIFOX_ACCESS_TOKEN 的环境变量,以避免 APIFOX_ACCESS_TOKEN 泄漏问题。<私有化部署服务器的 API 地址,以 http:// 或 https:// 开头>"。另外,请确保网络可以正常访问 www.npm.com。"--project-id=<project-id>" 参数,添加 "--oas=<oas-url-or-path>" 参数。如:npx apifox-mcp-server --oas https://petstore.swagger.io/v2/swagger.json 或 npx apifox-mcp-server --oas ~/data/petstore/swagger.jsonApifox MCP Server 还在内测阶段,欢迎各位给我们提建议和想法,请加内测群:

Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.