Proxy MCP
proxy-mcp is an MCP server that provides HTTP/HTTPS man-in-the-middle proxy functionality, supports traffic capture, real-time modification, TLS fingerprint camouflage, and upstream proxy chains, and includes a variety of interceptor tools for automated proxy configuration of browsers, command lines, Docker, and Android devices.
2.5 points
7.1K

What is proxy-mcp?

proxy-mcp is a man-in-the-middle proxy server based on the Model Context Protocol (MCP). It allows you to intercept, inspect, and modify all HTTP and HTTPS network traffic passing through it. You can think of it as a 'microscope' and 'editor' for network traffic, capable of both observing the details of network communication and modifying them in real-time as the data flows.

How to use proxy-mcp?

Using proxy-mcp is very simple: First, start the proxy server, and then configure your application (such as a browser) to use this proxy. proxy-mcp provides a variety of 'interceptor' tools that can automatically complete the configuration process. Once the traffic starts flowing, you can view and search the traffic, set rules to modify requests, and even camouflage your browser fingerprint.

Use cases

proxy-mcp is very suitable for the following scenarios: • Network security testing and vulnerability mining • Web crawler development and debugging • API interface testing and simulation • Browser automation and anti-detection research • Mobile application network behavior analysis • Network performance monitoring and optimization

Main features

Traffic capture and analysis
Capture all HTTP/HTTPS requests and responses passing through the proxy in real-time, providing detailed viewing and search functions. Support filtering by conditions such as hostname, method, and status code.
Real-time traffic modification
Modify requests and responses during traffic transmission. You can add, delete, or modify HTTP headers, rewrite URLs, return simulated responses, or even directly discard requests.
TLS fingerprint camouflage
Run curl-impersonate through Docker/Podman containers to camouflage the TLS and HTTP/2 fingerprints of outbound requests as those of real browsers (such as Chrome, Firefox), effectively bypassing fingerprint-based detection.
Intelligent interceptors
Provide a variety of interceptors that can automatically configure different applications to use the proxy: • Chrome/Chromium/Brave/Edge browsers • Command-line tools and processes • Android devices (via ADB) • Android applications (via Frida) • Docker containers
Upstream proxy chain
Support forwarding traffic to upstream proxies (such as SOCKS5, HTTP proxies) to achieve geographical location camouflage or access restricted networks. You can set global proxies or proxy rules for specific hosts.
Persistent sessions
Save traffic records to disk, support importing/exporting HAR files, querying historical sessions, and replaying captured requests. Even if the proxy restarts, the data will not be lost.
Humanized browser operations
Simulate real human mouse movements, clicks, typing, and scrolling behaviors through the Chrome DevTools Protocol. Use Bezier curves, Fitts' law, and natural typing rhythms to effectively bypass behavior detection.
DevTools bridging
Securely bind to the Chrome instance started by the interceptor, providing full DevTools functionality: screenshots, network request lists, console messages, cookie and local storage management.
Advantages
Comprehensive functionality: Integrates traffic capture, modification, fingerprint camouflage, and automation.
Easy to use: Provides interceptor automatic configuration, no need to manually set up the proxy.
Highly customizable: Supports complex rule matching and traffic processing logic.
Cross-platform: Supports multiple targets such as browsers, command lines, mobile devices, and containers.
Integrates with existing tools: Can be used in conjunction with tools such as Playwright and CDP.
Open source and transparent: Built on mature open-source libraries such as mockttp.
Limitations
Requires configuration: Target devices/applications need to trust the proxy's CA certificate to intercept HTTPS.
Performance overhead: As a man-in-the-middle proxy, it introduces some network latency.
Fingerprint camouflage depends on Docker: The TLS fingerprint camouflage function requires a Docker or Podman environment.
Some advanced features require additional permissions: For example, Android certificate injection requires root permissions.
Cannot capture all traffic: Can only capture traffic explicitly configured to pass through the proxy, not a network sniffer.

How to use

Installation and startup
First, install proxy-mcp and start the proxy server.
Configure the MCP client
Add the proxy-mcp server to the configuration file of your MCP client (such as Claude Code).
Start the proxy service
Execute the command in the MCP client to start the proxy server.
Configure the application to use the proxy
Use the interceptor to automatically configure the target application, or manually set up the proxy.
View and analyze traffic
After the traffic starts flowing, use the tool to view and analyze the captured data.

Usage examples

Website crawler development and debugging
When developing a web crawler, use proxy-mcp to view all network requests, modify request headers to bypass anti-crawling mechanisms, and camouflage the browser fingerprint.
API interface testing and simulation
When testing a mobile application, intercept its API requests, modify the response data, or return simulated responses to test various boundary conditions.
Security testing and vulnerability mining
In security testing, use proxy-mcp to intercept and modify requests to test the application's input validation, authentication, and authorization mechanisms.
Browser automation and anti-detection
When performing browser automation, use humanized operation tools to simulate real user behaviors and combine fingerprint camouflage to bypass automation detection.

Frequently Asked Questions

What is the difference between proxy-mcp and an ordinary proxy server?
Is it safe to use proxy-mcp to intercept HTTPS traffic?
How does TLS fingerprint camouflage work?
Can I capture the traffic of multiple applications simultaneously?
How to solve the 'Certificate not trusted' error?
Will proxy-mcp affect the network speed?
Can I save and replay the captured traffic?
How to use proxy-mcp with Playwright or Puppeteer?

Related resources

GitHub repository
Source code and latest version of proxy-mcp
Model Context Protocol documentation
Official documentation and specifications of the MCP protocol
mockttp project
HTTP simulation and testing library on which proxy-mcp is based
curl-impersonate project
A curl branch for TLS fingerprint camouflage
Chrome DevTools Protocol documentation
Reference for the Chrome Developer Tools Protocol
Frida framework
Cross-platform framework for dynamic instrumentation
Playwright documentation
Documentation for the browser automation framework

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "proxy": {
      "command": "node",
      "args": ["/path/to/proxy-mcp/dist/index.js"]
    }
  }
}

{
  "mcpServers": {
    "proxy": {
      "command": "proxy-mcp"
    }
  }
}

{
  "mcpServers": {
    "proxy": {
      "type": "streamable-http",
      "url": "http://127.0.0.1:3001/mcp"
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
5.4K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
5.4K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
5.5K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.7K
4 points
P
Paperbanana
Python
8.0K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
7.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.8K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
6.7K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
21.8K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
26.1K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.8K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.2K
5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
33.1K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.9K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
49.3K
4.8 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.3K
4.5 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase