MCPgee
MCPgee
MCPgeeMCPgee

Proxypin

v1.0.0•Monitoring & Observability•stable

自动化流量分析 mcp 工具

proxypinmcpai-integration
Share:
104
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Proxypin?

Proxypin is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 自动化流量分析 mcp 工具

自动化流量分析 mcp 工具

This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 自动化流量分析 mcp 工具

Use Cases

Automate network traffic analysis and monitoring. Capture and analyze HTTP/HTTPS traffic for debugging and optimization.
LunFengChen

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 18, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx proxypin

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Proxypin

The ProxyPin MCP Server is a Python-based integration that connects AI agents to ProxyPin, a cross-platform HTTP/HTTPS traffic capture proxy. It exposes 18 tools covering request search and replay, response and request rewriting, JavaScript script injection, HAR export and import, traffic statistics, API endpoint extraction, and proxy control — enabling AI assistants to inspect, manipulate, and automate network traffic analysis directly from a conversational interface. Developers and QA engineers use it to debug API calls, generate code snippets from captured requests, and automate traffic interception scenarios without switching tools.

Prerequisites

  • Python 3.10 or later
  • ProxyPin application installed and running (with MCP support, available from the ProxyPin repository)
  • fastmcp and requests Python packages installed
  • An MCP-compatible client such as Claude Desktop or VS Code with MCP support
  • ProxyPin MCP service listening on http://127.0.0.1:17777
1

Download and install ProxyPin with MCP support

Download the ProxyPin version that includes MCP support from the ProxyPin releases page. This version exposes the MCP API on port 17777 in addition to the standard capture port 9099.

2

Download the MCP server Python script

Download proxypin_mcp_server.py from the project releases and place it in a convenient location on your system.

3

Install Python dependencies

Install the required Python packages for the MCP server script.

pip install fastmcp requests
4

Start ProxyPin and the MCP server

Launch ProxyPin first to start capturing traffic on port 9099, then start the MCP server script which connects to ProxyPin's MCP API on port 17777.

python proxypin_mcp_server.py
5

Configure your MCP client

Add the ProxyPin MCP server to your AI client configuration, pointing to the Python script. Use the full path to both the Python interpreter and the script.

Proxypin Examples

Client configuration

Configure Claude Desktop to connect to the ProxyPin MCP server. Replace the paths with the actual locations on your system.

{
  "mcpServers": {
    "proxypin-mcp": {
      "command": "/usr/bin/python3",
      "args": ["/path/to/proxypin_mcp_server.py"],
      "disabled": false
    }
  }
}

Prompts to try

Use natural language to analyze and manipulate network traffic captured by ProxyPin.

- "Search for all requests to api.example.com in the last 5 minutes"
- "Show me the details of the most recent failed HTTP request"
- "Replay request ID 42 and show the response"
- "Generate Python requests code for the last POST to /api/login"
- "Export all captured traffic to a HAR file"
- "Block all requests to analytics.example.com"
- "Extract all unique API endpoints from today's captured traffic"

Troubleshooting Proxypin

MCP server cannot connect to ProxyPin on port 17777

Ensure you are running the ProxyPin version with MCP support enabled, not the standard release. ProxyPin must be started before the MCP server script. Check that port 17777 is not blocked by a firewall.

fastmcp or requests module not found

Run 'pip install fastmcp requests' in the same Python environment used to run the MCP server script. If using a virtual environment, activate it first.

AI client tools return empty results even when ProxyPin has captured traffic

Verify ProxyPin is actively capturing by checking the ProxyPin UI. The MCP server connects to port 17777, while traffic capture uses port 9099 — both must be active. Restart ProxyPin if the capture port is not listening.

Frequently Asked Questions about Proxypin

What is Proxypin?

Proxypin is a Model Context Protocol (MCP) server that 自动化流量分析 mcp 工具 It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Proxypin?

Follow the installation instructions on the Proxypin GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Proxypin?

Proxypin works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Proxypin free to use?

Yes, Proxypin is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Proxypin Alternatives — Similar Monitoring & Observability Servers

Looking for alternatives to Proxypin? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.

Netdata

★ 78.9k

Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.

Kubeshark

★ 11.9k

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.

Mission Control

★ 4.9k

Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.

Grafana

★ 3.0k

This MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.

Sentrux

★ 2.4k

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

OpenInference

★ 986

OpenTelemetry Instrumentation for AI Observability

Browse More Monitoring & Observability MCP Servers

Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Monitoring & ObservabilityBrowse All Servers

Quick Config Preview

{ "mcpServers": { "proxypin": { "command": "npx", "args": ["-y", "proxypin"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Proxypin?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides