Anything Analyzer
全能协议分析工具：浏览器抓包 + MITM 代理 + 指纹伪装 + AI 分析 + MCP Server 无缝对接 AI Agent/IDE | All-in-one protocol analysis toolkit — built-in browser capture, MITM proxy, JS hooks, fingerprint spoofing, AI analysis & MCP server for agent integration
What is Anything Analyzer?
Anything Analyzer is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 全能协议分析工具：浏览器抓包 + mitm 代理 + 指纹伪装 + ai 分析 + mcp server 无缝对接 ai agent/ide | all-in-one protocol analysis toolkit — built-in browser capture, mitm proxy, js hooks, fingerprint spoofing, ai analysis & mcp ...
全能协议分析工具：浏览器抓包 + MITM 代理 + 指纹伪装 + AI 分析 + MCP Server 无缝对接 AI Agent/IDE | All-in-one protocol analysis toolkit — built-in browser capture, MITM proxy, JS hooks, fingerprint spoofing, AI analysis & MCP server for agent integration
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 全能协议分析工具：浏览器抓包 + MITM 代理 + 指纹伪装 + AI 分析 + MCP Server 无缝对接 AI
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx anything-analyzerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Anything Analyzer
Anything Analyzer is an all-in-one Electron desktop application for network protocol analysis that combines a built-in browser with CDP-based capture, a full MITM HTTPS proxy on port 8888, JS hook injection for intercepting crypto calls, and a two-phase AI analysis pipeline — all feeding into an MCP server that AI agents like Claude Desktop and Cursor can call directly. It captures traffic from web pages, desktop apps, CLI tools, Python/Node scripts, mobile devices, and IoT devices into a unified session, then uses your configured LLM to automatically reverse-engineer APIs, detect security issues, and extract encryption logic. Security researchers and API reverse-engineers use it to understand undocumented protocols without manually sifting through hundreds of requests.
Prerequisites
- Windows, macOS (Apple Silicon or Intel), or Linux desktop OS
- An AI provider API key (OpenAI, Anthropic, or any OpenAI-compatible endpoint) configured in Settings → LLM
- Administrator/sudo rights for installing the MITM CA certificate
- An MCP-compatible client such as Claude Desktop or Cursor if using the built-in MCP server
- For mobile capture: a device on the same Wi-Fi network as the computer running Anything Analyzer
Download and install the application
Download the platform-specific installer from the GitHub Releases page and install it normally.
# Download from: https://github.com/Mouseww/anything-analyzer/releases
# Windows: Anything-Analyzer-Setup-x.x.x.exe
# macOS Apple Silicon: Anything-Analyzer-x.x.x-arm64.dmg
# macOS Intel: Anything-Analyzer-x.x.x-x64.dmg
# Linux: Anything-Analyzer-x.x.x.AppImageConfigure your LLM API key
Open Settings → LLM and enter your API key. Anything Analyzer supports OpenAI, Anthropic, and any OpenAI Chat Completions-compatible endpoint.
Install the MITM CA certificate
For capturing HTTPS traffic from desktop apps, CLI tools, or mobile devices, install the CA certificate. Go to Settings → MITM proxy → Install CA Certificate. Administrator or sudo rights are required.
Capture web traffic using the built-in browser
Create a new Session, enter the target URL, open the built-in browser, interact with the site to generate traffic, then click Start Capture.
Capture desktop app or CLI traffic via MITM proxy
Enable the MITM proxy in Settings (default port 8888), then configure your application or terminal to route traffic through it.
# Terminal / curl
curl -x http://127.0.0.1:8888 https://api.example.com/data
# Python requests
import requests
proxies = {"http": "http://127.0.0.1:8888", "https": "http://127.0.0.1:8888"}
requests.get("https://api.example.com/data", proxies=proxies, verify=False)
# Node.js
HTTP_PROXY=http://127.0.0.1:8888 HTTPS_PROXY=http://127.0.0.1:8888 node app.jsTrigger AI analysis on captured traffic
Stop the capture, click Analyze, and choose an analysis mode: Auto, API Reverse Engineering, Security Audit, Performance Analysis, or JS Encryption Reverse Engineering. Results stream in real time and you can ask follow-up questions.
Anything Analyzer Examples
Client configuration
Add the Anything Analyzer built-in MCP server to Claude Desktop so Claude can invoke capture and analysis tools programmatically.
{
"mcpServers": {
"anything-analyzer": {
"command": "npx",
"args": ["anything-analyzer"]
}
}
}Prompts to try
Example prompts for Claude once Anything Analyzer is connected as an MCP server.
- "Capture all network traffic from the built-in browser session on https://api.example.com and produce an API reverse-engineering report."
- "Analyse the captured requests for token leakage, CSRF vulnerabilities, and exposed sensitive data."
- "Extract and document the JavaScript encryption logic used in the login flow of the captured session."
- "Show me the authentication flow from the last capture session and generate a Python script to reproduce it."Troubleshooting Anything Analyzer
HTTPS traffic from desktop apps shows as CONNECT tunnels instead of decrypted requests
The MITM CA certificate must be installed and trusted system-wide. Go to Settings → MITM → Install CA Certificate and confirm the prompt with administrator credentials. On macOS you may also need to trust the certificate manually in Keychain Access (mark it as Always Trust for SSL). Reinstall the certificate and restart the target application.
AI analysis returns empty or generic results
Verify your LLM API key is correctly entered in Settings → LLM and that the model endpoint is reachable. The two-phase analysis requires the LLM to make multiple calls; if you are using a rate-limited free tier, the second phase may time out. Try running analysis on a smaller, manually selected subset of requests using the multi-select mode.
Mobile device traffic does not appear in the session
Ensure the mobile device is on the same Wi-Fi network as the computer. Set the device's Wi-Fi proxy to Manual, enter the computer's local IP address, and use port 8888. Then visit the proxy address in the mobile browser to download and install the CA certificate — on iOS you must also go to Settings → General → About → Certificate Trust Settings and enable full trust for the installed certificate.
Frequently Asked Questions about Anything Analyzer
What is Anything Analyzer?
Anything Analyzer is a Model Context Protocol (MCP) server that 全能协议分析工具：浏览器抓包 + mitm 代理 + 指纹伪装 + ai 分析 + mcp server 无缝对接 ai agent/ide | all-in-one protocol analysis toolkit — built-in browser capture, mitm proxy, js hooks, fingerprint spoofing, ai analysis & mcp server for agent integration It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Anything Analyzer?
Follow the installation instructions on the Anything Analyzer GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Anything Analyzer?
Anything Analyzer works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Anything Analyzer free to use?
Yes, Anything Analyzer is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Anything Analyzer Alternatives — Similar Security Servers
Looking for alternatives to Anything Analyzer? Here are other popular security servers you can use with Claude, Cursor, and VS Code.
Casdoor
★ 13.6kAn open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD
ghidraMCP
★ 9.0kAn Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through
HexStrike AI
★ 8.9kHexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly b
IDA Pro MCP
★ 8.7kEnables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.
Anthropic Cybersecurity Skills
★ 6.6k754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform
Hooker
★ 5.1k🔥🔥 hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u
Browse More Security MCP Servers
Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Anything Analyzer in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Anything Analyzer?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.