MCP-APIKit
MCP-API工具包
MCP-APIKit 是一个专为 Windsurf IDE 集成设计的微服务控制平面 (MCP) 服务器。它从 Eolink OpenAPI 获取 API 信息并将其提供给 IDE 的 MCP 客户端,从而实现开发环境中 API 的无缝集成和管理。
特征
连接到 Eolink OpenAPI 以检索 API 规范
将 API 信息公开为 MCP 资源
提供 API 发现和探索工具
支持 Windsurf IDE 中的 API 测试和集成
实现模型上下文协议 (MCP) 以实现标准化通信
Related MCP server: MCP-FEISHU
安装
# Clone the repository
git clone https://github.com/yourusername/mcp-apikit.git
cd mcp-apikit
# Install dependencies
pnpm install
# Build the project
pnpm run build配置
在根目录中创建一个.env文件,其中包含以下变量:
EOLINK_API_KEY=your_eolink_api_key
EOLINK_BASE_URL=https://api.eolink.com
SPACE_ID=your_space_id
PROJECT_ID=your_project_id用法
启动服务器
pnpm start服务器将在您的.env文件中指定的端口上启动(默认值:3000)。
调试
npx @modelcontextprotocol/inspector node dist/index.js从 Windsurf IDE 连接
pnpm build在您的 Windsurf IDE 设置中,添加一个具有以下配置的新 MCP 服务器:
"mcpServers": {
"apikit": {
"command": "node",
"args": [
"/Users/{userName}/Documents/mcp-apikit/dist/index.js"
],
"env": {}
}
}API 资源
MCP-APIKit 服务器公开以下资源:
api://projects- 列出所有 API 项目api://projects/{projectId}- 获取特定项目的详细信息api://projects/{projectId}/apis- 列出项目中的所有 APIapi://projects/{projectId}/apis/{apiId}- 获取特定 API 的详细信息
工具
该服务器提供以下工具:
search-apis- 在所有项目中搜索 APItest-api- 使用自定义参数测试 API 端点import-api- 将 API 规范从 Eolink 导入到您的项目
发展
# Run in development mode with hot reloading
npm run dev执照
麻省理工学院
Available Tools
6 toolsget_apiD
Inputs: projectId (required), apiId (required).
get_projectD
Inputs: projectId (required).
list_apisD
Inputs: projectId, spaceId.
list_projectsD
Inputs: no named parameters.
search_apisD
Inputs: query (required).
test_apiD
Inputs: projectId (required), apiId (required), headers, queryParams, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no overlap: get_api retrieves a single API, list_apis lists multiple APIs, search_apis searches APIs, get_project retrieves a single project, list_projects lists multiple projects, and test_api tests an API. The resource-action pairs are unambiguous and well-defined.
All tool names follow a consistent verb_noun pattern with snake_case: get_api, get_project, list_apis, list_projects, search_apis, test_api. The naming is perfectly predictable and uniform throughout the set.
With 6 tools, the count is reasonable for managing APIs and projects, but it feels slightly thin as it lacks update or delete operations. However, it covers core retrieval and listing functions adequately for a basic API management scope.
The tool set covers retrieval and listing for APIs and projects, plus searching and testing for APIs, but there are notable gaps: no create, update, or delete operations for either resource. This limits full lifecycle management and may cause agent failures for modification tasks.
Maintenance
Related MCP Connectors
MCP server for AI access to Swagger by SmartBear.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA Python-based MCP server that integrates OpenAPI-described REST APIs into MCP workflows, enabling dynamic exposure of API endpoints as MCP tools.157MIT
- AlicenseDqualityDmaintenanceA microservice control plane server that fetches API information from Feishu OpenAPI and provides it to Windsurf IDE, enabling seamless API integration and management within your development environment.2MIT
- AlicenseNot gradedqualityDmaintenanceMCP Server for the Edgee API, enabling organization management, project operations, component management, and user administration through the Model Context Protocol.Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA universal MCP server that connects any REST API to AI assistants via OpenAPI or Postman specifications. It enables dynamic tool creation with GraphQL-style field selection and automatic schema inference for efficient data retrieval.42 npm6-