Proxyman MCP
Proxyman MCP allows AI to inspect HTTP traffic, create debugging rules, and control Proxyman - all through natural language conversations.
Ads
Overview
> For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to page URLs; this page is available as Markdown. Proxyman MCP (Model Context Protocol) is a feature that enables AI assistants (Claude, Cursor, and other MCP-compatible tools) to directly interact with the Proxyman macOS app. It allows AI to inspect HTTP traffic, create debugging rules, and control Proxyman - all through natural language conversations. The architecture consists of two components:
Installation
claude mcp add proxyman --transport stdio -- "/Applications/Proxyman.app/Contents/MacOS/mcp-server"
Configuration
{
"mcpServers": {
"proxyman": {
"command": "/Applications/Proxyman.app/Contents/MacOS/mcp-server"
}
}Capabilities
- Inspect captured traffic
Ask the AI to list recent HTTP flows with `get_flows` and drill into full request/response details with `get_flow_detail`.
- Create debugging rules via conversation
Set up breakpoints, map local, map remote, or blacklist rules using `create_breakpoint`, `create_map_local`, `create_map_remote`, and `create_blacklist`.
- Control the proxy session
Start or stop recording with `toggle_recording` and clear all captured flows with `clear_session`.
- Export requests as code
Export a captured flow as a cURL command with `export_flow_curl` or generate client code in 18+ languages using `generate_code`.
- Manage SSL decryption
Enable HTTPS decryption for a domain with `enable_ssl_proxying` and check certificate installation status via `get_certificate_status`.
- Configure advanced proxy settings
Set an upstream external proxy with `set_external_proxy`, create reverse proxy entries with `create_reverse_proxy`, or toggle no-caching behavior.
Tags
- debugging
- development
- network-automation
- testing-qa
Related MCP servers
Context7 MCP
OfficialOfficial Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.
Chrome DevTools MCP
OfficialOfficial Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.
Mastra/mcp
OfficialClient implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.
GitHub MCP Server
OfficialConnect your AI assistant to GitHub repositories, issues, pull requests, and search.