mcp-api-tools
A comprehensive suite of HTTP and API testing tools that enables AI agents to perform requests, check endpoint health, and decode JWTs. It also provides utilities for URL parsing and detailed security analysis of HTTP response headers.
README
@rog0x/mcp-api-tools
HTTP/API testing tools for AI agents, built on the Model Context Protocol.
Tools
http_request
Make any HTTP request (GET, POST, PUT, DELETE, PATCH, HEAD, OPTIONS) with full control over headers, body, authentication, and timeouts. Returns status code, response headers, body, and timing information.
api_health
Check the health of multiple API endpoints in parallel. Returns HTTP status, response time, SSL certificate validity and expiry, and optional response body validation. Includes a summary with counts of healthy, unhealthy, and errored endpoints.
jwt_decode
Decode a JWT token without cryptographic verification. Returns the decoded header and payload, issued-at time, expiry time, and whether the token is currently expired.
url_parse
Parse a URL into its component parts (protocol, host, port, path, query parameters, hash) or build a URL from individual parts.
header_analyzer
Analyze HTTP response headers for security posture (HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy), caching directives, CORS configuration, and cookie attributes. Provides a letter grade for security. Can fetch headers from a live URL or analyze a provided headers object.
Installation
npm install
npm run build
Configuration
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"api-tools": {
"command": "node",
"args": ["D:/products/mcp-servers/mcp-api-tools/dist/index.js"]
}
}
}
Claude Code
claude mcp add api-tools node D:/products/mcp-servers/mcp-api-tools/dist/index.js
Examples
Make a POST request:
Use http_request to POST to https://httpbin.org/post with JSON body {"key": "value"}
Check API health:
Use api_health to check these endpoints: https://api.github.com, https://httpbin.org/get
Decode a JWT:
Use jwt_decode to decode this token: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...
Parse a URL:
Use url_parse to break down https://example.com:8080/api/v1?key=value&debug=true#section
Analyze security headers:
Use header_analyzer to check security headers for https://github.com
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。