Apifox MCP Server
A Model Context Protocol (MCP) server for Apifox API management with read/write/import capabilities.
README
Apifox MCP Server
A Model Context Protocol (MCP) server for Apifox API management with read/write/import capabilities, based on Apifox Open API.
Features
Read Operations
apifox_get_project- Get project detailsapifox_get_folders- Get folder list (directory structure)apifox_get_endpoints- Get API endpoint listapifox_get_endpoint- Get endpoint detailsapifox_get_schemas- Get data model listapifox_export_openapi- Export as OpenAPI format
Write Operations
apifox_create_folder- Create folderapifox_create_endpoint- Create API endpointapifox_update_endpoint- Update API endpointapifox_delete_endpoint- Delete API endpointapifox_create_schema- Create data model
Import Operations
apifox_import_openapi- Import OpenAPI/Swagger dataapifox_import_openapi_from_url- Import OpenAPI data from URL
Installation
From npm
npm install -g apifox-mcp-server
From source
git clone https://github.com/lishuji/apifox-mcp-server.git
cd apifox-mcp-server
npm install
npm run build
Configuration
1. Get API Access Token
- Login to Apifox
- Click avatar in top right → Account Settings
- Click "API Access Token" → Create new token
- Save the generated token
2. Get Project ID
- Open your Apifox project
- The number in the project URL is the project ID, e.g.,
4051641inhttps://apifox.com/project/4051641
3. Configure MCP Client
Add to your MCP client configuration (e.g., ~/.codebuddy/mcp.json for CodeBuddy):
{
"mcpServers": {
"Apifox": {
"command": "npx",
"args": [
"apifox-mcp-server",
"--project=YOUR_PROJECT_ID"
],
"env": {
"APIFOX_ACCESS_TOKEN": "YOUR_ACCESS_TOKEN"
}
}
}
}
Or if installed globally:
{
"mcpServers": {
"Apifox": {
"command": "apifox-mcp-server",
"args": [
"--project=YOUR_PROJECT_ID"
],
"env": {
"APIFOX_ACCESS_TOKEN": "YOUR_ACCESS_TOKEN"
}
}
}
}
Usage Examples
Import OpenAPI Data
// Read local OpenAPI file content
const spec = fs.readFileSync('openapi.yaml', 'utf-8');
// Call import tool
apifox_import_openapi({
spec: spec,
targetFolderId: 12345, // Target folder ID
coverExistApi: true, // Overwrite existing APIs
syncFolder: true // Sync folder structure
});
Create Endpoint
apifox_create_endpoint({
name: "Get User List",
method: "GET",
path: "/api/v1/users",
folderId: 12345,
description: "Paginated user list",
tags: ["User Management"]
});
Create Folder
apifox_create_folder({
name: "User APIs",
parentId: 0 // 0 means root directory
});
API Reference
apifox_import_openapi
Import OpenAPI/Swagger specification data.
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
| spec | string | Yes | OpenAPI spec content (JSON/YAML) |
| targetFolderId | number | No | Target folder ID, default 0 (root) |
| coverExistApi | boolean | No | Overwrite existing APIs, default true |
| coverExistSchema | boolean | No | Overwrite existing schemas, default true |
| syncFolder | boolean | No | Sync folder structure, default true |
apifox_create_endpoint
Create a new API endpoint.
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
| name | string | Yes | Endpoint name |
| method | string | Yes | HTTP method (GET, POST, PUT, DELETE, PATCH) |
| path | string | Yes | Endpoint path |
| folderId | number | No | Parent folder ID |
| description | string | No | Endpoint description |
| tags | string[] | No | Tag list |
Notes
- API Version: Uses
X-Apifox-Api-Version: 2024-03-28header - Authentication: Bearer Token authentication
- Rate Limiting: Be aware of Apifox API rate limits
- Permissions: Ensure token has sufficient project operation permissions
Related Links
License
MIT License - see LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。