http-inspector

http-inspector

HTTP Inspector MCP Server enables sending arbitrary HTTP requests, viewing history via a web panel, and taking screenshots of the panel for AI penetration testing workflows.

Category
Visit Server

README

HTTP Inspector MCP Server

基于 Streamable HTTP 的 MCP 服务器，集成 Web 面板与截图功能。
单进程、单端口 — 一站式 HTTP 流量检测工具箱。
解决AI自动化渗透测试后续需要人工复现截图的问题。

功能

  • 发送任意 HTTP 请求 — 支持全部方法、自定义 Header/Body、代理、超时（类似 Burp Repeater）
  • Web 面板 — 实时流量历史表格（SSE 推送）、Raw HTTP 详情视图、手动发送面板
  • 截图 — AI 可调用 screenshot_panel 截图 Web 面板，返回 PNG 文件 URL
  • Streamable HTTP — MCP 客户端通过 http://localhost:9876/mcp 连接

快速开始

# 安装依赖
cd mcp-http-inspector
pip install -e .

# 安装 Chromium 浏览器（用于截图）
# 项目 browsers/ 目录已内置 linux/mac-arm/win64 三平台 Chrome
# 无需额外安装，启动时自动检测

# 运行
python server.py

浏览器打开 http://localhost:9876 查看 Web 面板。

MCP 客户端配置

{
  "mcpServers": {
    "http-inspector": {
      "url": "http://localhost:9876/mcp"
    }
  }
}

MCP 工具

工具 说明
send_http_request 发送任意 HTTP 请求，支持 auto_screenshot 一步获取截图
list_history 列出请求历史，支持过滤和分页（不返回 raw body）
get_request_detail 按 ID 获取原始 HTTP 请求/响应（默认截断 5000 字符）
screenshot_panel 截图 Web 面板（history/detail/sender），返回 PNG 下载 URL
screenshot_last_request 快捷截图最新请求的 Detail，无需传 ID
clear_all_history 清空所有历史记录和截图文件

更多使用指南见 .reasonix/skills/http-inspector/SKILL.md

架构

MCP 客户端 ──HTTP──▶ :9876/mcp (Streamable HTTP)
浏览器     ──HTTP──▶ :9876/    (Web 面板 SPA)
                     :9876/api/* (REST + SSE)
                            │
                     httpx ──▶ 目标服务器
                     SQLite ◀── 历史存储
                     Playwright ──▶ 截图

支持平台

自动检测 OS 选择内置 Chrome 浏览器：

系统 路径
Linux x64 browsers/chrome-linux64/chrome
macOS ARM browsers/chrome-mac-arm64/.../Google Chrome for Testing
Windows x64 browsers/chrome-win64/chrome.exe

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured