rest-api-mcp
A lightweight MCP server that enables LLMs to interact with any REST API via HTTP requests, with smart response truncation, TypeScript type generation, and field extraction.
README
rest-api-mcp
A lightweight Model Context Protocol (MCP) server that lets LLMs interact with any REST API. It executes HTTP requests and provides optimized response analysis, including automatic TypeScript interface generation from live API responses.
Features
- Full HTTP support — GET, POST, PUT, DELETE, PATCH, HEAD, OPTIONS
- Smart response truncation — large JSON payloads are intelligently reduced (arrays sliced, structure preserved) instead of being cut mid-string
- TypeScript type generation — automatically derives TypeScript interfaces from API response structures
- Response structure analysis — inspect keys, types, and array lengths without returning the full body
- Field extraction — pull specific fields using dot-notation paths (e.g.
data.items[].name) - Flexible authentication — bearer token resolution chain: project
.env.mcpfile → MCP config env var → session token - Custom headers — inject global headers via
HEADER_*environment variables - Zero external runtime dependencies — uses only the MCP SDK and Node.js built-in
fetch
Tools
| Tool | Description |
|---|---|
rest_request |
Execute a request and return the full (smart-truncated) response |
rest_describe |
Execute a request and return the response structure + generated TypeScript interfaces (no full body) |
rest_types |
Execute a request and return only the generated TypeScript interfaces |
rest_extract |
Execute a request and extract specific fields by dot-notation paths |
rest_set_token |
Set a bearer token for the current session |
Installation
Prerequisites
- Node.js >= 18.0.0
- pnpm (or npm/yarn)
Build from source
git clone <repository-url>
cd rest-api-mcp
pnpm install
pnpm build
Configure in your MCP client
Add the server to your MCP client configuration (e.g. Claude Desktop claude_desktop_config.json):
{
"mcpServers": {
"rest-api": {
"command": "node",
"args": ["/path/to/rest-api-mcp/dist/index.js"],
"env": {
"REST_BASE_URL": "https://api.example.com",
"REST_BEARER_TOKEN": "your-token-here"
}
}
}
}
Configuration
All configuration is done via environment variables:
| Variable | Required | Description |
|---|---|---|
REST_BASE_URL |
Yes | Base URL for all API requests (e.g. https://api.example.com/v1) |
REST_BEARER_TOKEN |
No | Bearer token for authentication |
REST_RESPONSE_SIZE_LIMIT |
No | Max response size in bytes before smart truncation (default: 50000) |
REST_ENV_DIR |
No | Additional directory to search for .env.mcp files containing REST_BEARER_TOKEN |
HEADER_* |
No | Custom headers injected into every request (e.g. HEADER_X_API_KEY=abc sends X-Api-Key: abc) |
Authentication
Bearer tokens are resolved in this order (first match wins):
- Project
.env.mcpfile —REST_BEARER_TOKENin a.env.mcpfile in the working directory orREST_ENV_DIR. Re-read on every request, so token rotation is supported without restarting the server. - MCP config env var —
REST_BEARER_TOKENset in the MCP server configuration. - Session token — set at runtime via the
rest_set_tokentool.
If a 401 or 403 response is received and no token is configured, the server returns an auth hint suggesting resolution steps.
Usage Examples
Basic request
rest_request({ method: "GET", endpoint: "/users" })
With query parameters
rest_request({ method: "GET", endpoint: "/users", query: { page: "1", limit: "10" } })
Generate TypeScript types from an endpoint
rest_types({ method: "GET", endpoint: "/users/1", typeName: "User" })
Describe response structure
rest_describe({ method: "GET", endpoint: "/products", typeName: "ProductList" })
Extract specific fields
rest_extract({ method: "GET", endpoint: "/orders", fields: ["data[].id", "data[].status", "meta.total"] })
Development
# Watch mode with hot reload
pnpm dev
# Build for production
pnpm build
# Run the built server
pnpm start
License
MIT
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。