Burp Suite MCP Analyzer

Burp Suite MCP Analyzer

An MCP server that lets AI assistants analyze Burp Suite XML exports offline, without running Burp. Provides 19 tools for mapping endpoints, finding secrets, detecting vulnerabilities, analyzing headers, exporting curl commands, and generating pentest reports.

Category
访问服务器

README

🔥 Burp Suite MCP Analyzer

An MCP (Model Context Protocol) server that lets AI assistants analyze Burp Suite XML exports — offline, no Burp running required.

Ask AI (or any MCP-compatible AI) to map endpoints, find secrets, detect vulnerabilities, analyze headers, export curl commands, and generate pentest reports — all from a Burp XML export file.


✨ Features — 19 Tools

Category Tools
Core load_burp_file, explore_file_structure, get_statistics, generate_report
Traffic get_proxy_history, analyze_request, search_requests, find_errors
Recon find_endpoints, find_parameters, get_cookies, detect_technologies, find_interesting_paths, find_file_uploads
Security get_vulnerabilities, find_sensitive_data, analyze_security_headers, find_injection_points, export_as_curl

📋 Prerequisites

  • Python 3.10+
  • Any MCP-compatible AI client (Claude Desktop, Claude Code, OpenCode, Cursor, GitHub Copilot, Windsurf)
  • Burp Suite (any version — just for exporting XML)

🚀 Installation

1. Clone the repo

git clone https://github.com/YOUR_USERNAME/burp-mcp-analyzer.git
cd burp-mcp-analyzer

2. Install dependencies

pip install -r requirements.txt

3. Configure your AI client — see Configuration below


📤 Exporting from Burp Suite

The server works with Burp XML exports (not raw .burp project files).

Option A — Proxy history only (quickest):

Proxy tab → HTTP History → Ctrl+A (select all)
→ Right-click → Save items → save as export.xml

Option B — Site map scanner issues:

Target tab → Site map → Select URL → Under Contents → Right-click → Save items → save as export.xml

⚙️ Configuration

Claude Desktop

Edit %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (Mac):

{
  "mcpServers": {
    "burp-analyzer": {
      "command": "python3",
      "args": ["/path/to/burp_mcp_server.py"]
    }
  }
}

Windows with WSL:

{
  "mcpServers": {
    "burp-analyzer": {
      "command": "wsl.exe",
      "args": ["python3", "/home/YOUR_USERNAME/burp-mcp-analyzer/burp_mcp_server.py"]
    }
  }
}

Claude Code

claude mcp add burp-analyzer python3 /path/to/burp_mcp_server.py

Or import from Claude Desktop if already configured:

claude mcp add-from-claude-desktop

OpenCode

Edit ~/.config/opencode/config.json:

{
  "mcpServers": {
    "burp-analyzer": {
      "command": "python3",
      "args": ["/path/to/burp_mcp_server.py"],
      "type": "stdio"
    }
  }
}

GitHub Copilot (VS Code)

Create .vscode/mcp.json in your project:

{
  "servers": {
    "burp-analyzer": {
      "type": "stdio",
      "command": "python3",
      "args": ["/path/to/burp_mcp_server.py"]
    }
  }
}

Cursor

Edit ~/.cursor/mcp.json:

{
  "mcpServers": {
    "burp-analyzer": {
      "command": "python3",
      "args": ["/path/to/burp_mcp_server.py"]
    }
  }
}

Windsurf

Edit ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "burp-analyzer": {
      "command": "python3",
      "args": ["/path/to/burp_mcp_server.py"]
    }
  }
}

Restart your AI client after editing config files.


💬 Usage

Once configured, load a Burp XML export and start asking:

Load this file: /path/to/export.xml

Example Prompts

Recon

Show me all unique endpoints and paths discovered

Security Analysis

Scan all traffic for secrets, API keys, and credentials
Check all responses for missing or misconfigured security headers

Traffic

Show me all POST requests that returned 200
Find all 500 errors with the full response body

Reporting

Generate a full penetration test report with all findings

Chained

Load the file, map all endpoints, find injection points, then tell me the top 3 things to test
Find all sensitive data exposed in responses and group by risk level

For a full list of example prompts, see PROMPTS.md.


🔍 Sensitive Data Patterns Detected

The server automatically scans for 20+ patterns:

  • JWT Tokens, Bearer Tokens, Basic Auth
  • AWS Access Keys & Secret Keys
  • Google API Keys, GitHub Tokens, Slack Tokens, Stripe Keys, SendGrid Keys
  • Passwords in URLs and request bodies
  • Database connection strings
  • Private keys (RSA, EC)
  • Session cookies (PHPSESSID, JSESSIONID, connect.sid)
  • SQL errors and stack traces
  • Internal IP addresses
  • Email addresses, Credit card numbers

🛡️ Security Headers Checked

Strict-Transport-Security · Content-Security-Policy · X-Frame-Options · X-Content-Type-Options · Referrer-Policy · Permissions-Policy · Cache-Control · Access-Control-Allow-Origin


🗂️ Supported File Formats

Format How to get it
Burp XML export (.xml) Proxy → HTTP History → Save items
Gzip-compressed XML Project → Save copy (some Burp versions)

Raw .burp project files are not supported — they use a proprietary binary format. Use the XML export instead.


⚠️ Legal & Ethical Use

This tool is intended for authorized security testing only.

  • Only analyze traffic from systems you have explicit permission to test
  • Unauthorized interception or analysis of network traffic may be illegal
  • The authors are not responsible for misuse of this tool

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选