API Debugger MCP
API Debugger MCP 🚀
基于 FastMCP 构建的、面向生产环境的 Model Context Protocol (MCP) 服务器,用于检查、测试、验证、比较和调试 HTTP API。
为什么做这个项目?
API 故障的排查往往需要在 API 客户端、OpenAPI 文档、日志、测试套件和 bug 跟踪器之间来回切换。API Debugger MCP 为兼容 MCP 的 AI 代理提供了一套结构化工具包,以便执行这些调查工作。
Related MCP server: mcp-api-tools
功能特性
12 个 MCP 工具,用于 API 调试和 QA
对常见凭据字段和请求头进行安全的敏感信息脱敏
可配置的超时和响应大小限制
默认阻止私有/本地网络访问
JSON-schema 风格的响应契约验证
响应体之间的回归比较
多端点健康检查
自动化 API 测试场景生成
结构化 bug 报告生成
端到端事件调查工作流
MCP 资源和可复用的提示词
Docker 支持
Pytest + coverage
Ruff 代码检查
支持 Python 3.10–3.12 的 GitHub Actions CI
MCP 工具
inspect_endpointsend_requestvalidate_responsecompare_responsesanalyze_errordetect_api_issuegenerate_api_testsgenerate_bug_reportcheck_contractapi_health_checkredact_sensitive_datainvestigate_incident
项目结构
api-debugger-mcp/
├── .github/workflows/ci.yml
├── docs/
├── src/api_debugger_mcp/
│ ├── analysis.py
│ ├── client.py
│ ├── config.py
│ ├── models.py
│ ├── security.py
│ ├── server.py
│ └── tools.py
├── tests/
├── .dockerignore
├── .env.example
├── .gitignore
├── Dockerfile
├── LICENSE
├── Makefile
├── docker-compose.yml
└── pyproject.toml快速开始
1. 创建虚拟环境
python -m venv .venvWindows:
.venv\Scripts\activatemacOS/Linux:
source .venv/bin/activate2. 安装
pip install -e ".[dev]"3. 配置
将 .env.example 复制为 .env,并且只设置环境所需的值。
切勿提交真实环境中的 API 密钥或 bearer 令牌。
4. 本地运行
对于 HTTP MCP 服务器:
api-debugger-mcp默认 MCP 端点为:
http://localhost:8000/mcp对于本地 stdio 模式:
MCP_TRANSPORT=stdio然后运行:
api-debugger-mcpDocker
docker compose up --build服务器暴露在 8000 端口上。
测试
pytestLint(代码检查):
ruff check .格式化:
ruff format .示例 MCP 工作流
兼容 MCP 的代理可以这样组合工具使用:
investigate_incident
↓
inspect_endpoint
↓
send_request
↓
detect_api_issue
↓
analyze_error
↓
check_contract
↓
generate_bug_report用于回归测试:
send_request (baseline)
↓
send_request (current)
↓
compare_responses
↓
validate_response安全说明
该服务器的默认设计目标就是避免意外泄露凭据和不安全的网络访问。
常见的 auth/cookie/API-key 请求头会在返回结果中脱敏。
常见的敏感字段会被递归脱敏。
默认阻止对本地/私有网络地址的请求。
不要提交含真实凭据的
.env文件。生产环境中,将 MCP 服务器置于组织的身份验证和网络访问控制之后。
在敏感化环境中启用私有网络请求时,先增加明文访问白名单。
生产路线图
OpenAPI 3.x 导入和端点发现
OAuth/API-key 密钥提供者
持久化基线
Sentry/可观测系统集成
Jira/GitHub issue 创建
请求关联 ID
限流
审计日志
RBAC/身份验证
异步并行健康检查
支持长时间运行的调查的 MCP 任务/后台执行
许可证
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceEnables AI agents to dynamically discover and interact with APIs through Swagger/OpenAPI specifications and Postman collections using a strategic four-tool approach. It streamlines API integration by providing universal tools for endpoint discovery, detailed request information, and authenticated execution.1
- AlicenseAqualityDmaintenanceA 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.537MIT
- AlicenseAqualityDmaintenanceEnables testing and validation of APIs for AI agent compatibility, providing scores, grades, and actionable recommendations.3MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to perform comprehensive web application testing including visual, functional, performance, accessibility, and SEO analysis using browser automation without requiring API keys.
Related MCP Connectors
See, price, and control every tool call your AI agents make: policy checks, cost, and audit tools.
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Curated knowledge API for AI agents - skill packs, semantic search, validated patterns.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MahaR54/API-DEBUGGER-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server