Proxypin Mcp Server
About
Proxypin Mcp Server is a Model Context Protocol (MCP) server that integrates with the open‑source ProxyPin tool to expose your local HTTP capture history to MCP‑capable clients. It reads ProxyPin’s HAR files and provides tools for listing, searching, and analyzing captured requests, as well as generating API code…
Details
- License
- MIT
Explore
- Read local ProxyPin history (HAR)
- List/search/detail tools for captured requests
- API structure analysis and code generation
- Works with mainstream MCP clients (Windsurf / Cursor / Claude Desktop / Codex)
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Proxypin Mcp ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
1. Install and open ProxyPin
2. In ProxyPin History settings, enable “Cache Date” (required)
3. Ensure some capture history exists
4. Node.js (for npx) and uv (launcher supports both uvx and uv tool run)
| Variable | Description | Default |
|---|---|---|
| PROXYPIN_DATA_DIR | ProxyPin history directory | auto-detect |
| PROXYPIN_HAR_LIMIT | max HAR files scanned | 50 |
| PROXYPIN_MAX_BODY_SIZE | max body bytes kept | 102400 |
list_requests
list recent HTTP requests with filters.
get_request
fetch one request by ID.
search_requests
keyword search across URL and body.
analyze_api
group endpoint patterns for one domain.
get_domains
summarize captured domains and method counts.
generate_code
generate Python/JS/cURL snippets from a capture.
- list_requests: list recent HTTP requests with filters.
- get_request: fetch one request by ID.
- search_requests: keyword search across URL and body.
- analyze_api: group endpoint patterns for one domain.
- get_domains: summarize captured domains and method counts.
- generate_code: generate Python/JS/cURL snippets from a capture.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"proxypin mcp server": {
"proxypin": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"proxypin-mcp@latest"
]
}
}
}
}McpServers
{
"proxypin": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"proxypin-mcp@latest"
]
}
}
ProxyPin MCP Server is based on the Model Context Protocol (MCP). It works with the open source project ProxyPin to expose your local capture history to MCP-capable clients.
Features
- Read local ProxyPin history (HAR)
- List/search/detail tools for captured requests
- API structure analysis and code generation
- Works with mainstream MCP clients (Windsurf / Cursor / Claude Desktop / Codex)
Prerequisites
1. Install and open ProxyPin
2. In ProxyPin History settings, enable “Cache Date” (required)
3. Ensure some capture history exists
4. Node.js (for npx) and uv (launcher supports both uvx and uv tool run)
Installation
Run with npx
npx -y proxypin-mcp@latest
The NPX bridge tries uvx first, then automatically falls back to uv tool run.
Usage
Add the following configuration to your MCP client configuration file:
{
"mcpServers": {
"proxypin": {
"type": "stdio",
"command": "npx",
"args": ["-y", "proxypin-mcp@latest"]
}
}
}
> [!TIP]
> If your client does not support type, remove the field.
Environment Variables
| Variable | Description | Default |
|---|---|---|
| PROXYPIN_DATA_DIR | ProxyPin history directory | auto-detect |
| PROXYPIN_HAR_LIMIT | max HAR files scanned | 50 |
| PROXYPIN_MAX_BODY_SIZE | max body bytes kept | 102400 |
Available Tools
list_requests
List recent captured requests.
Parameters:
- limit (int, optional, default 20)
- detail (string: summary | key | full)
- domain (string, optional)
- method (string, optional)
- status (int, optional)
get_request
Get a single request detail by ID.
Parameters:
- request_id (string, required)
- include_body (boolean, optional, default true)
search_requests
Search requests by keyword.
Parameters:
- keyword (string, required)
- search_in (string: all | url | request_body | response_body)
- limit (int, optional, default 20)
analyze_api
Analyze API structure for a domain.
Parameters:
- domain (string, required)
get_domains
List captured domains with counts.
Parameters:
- none
generate_code
Generate API call code from a captured request.
Parameters:
- request_id (string, required)
- language (string: python | javascript | typescript | curl)
- framework (string: requests | httpx | fetch | axios)
Skills (Tools)
- list_requests: list recent HTTP requests with filters.
- get_request: fetch one request by ID.
- search_requests: keyword search across URL and body.
- analyze_api: group endpoint patterns for one domain.
- get_domains: summarize captured domains and method counts.
- generate_code: generate Python/JS/cURL snippets from a capture.
Prompts
- analyze_api_prompt(domain): guide API structure analysis workflow.
- debug_request_prompt(request_id): guide request debugging workflow.
Resources
- proxypin://requests/recent: recent request summary dataset.
- proxypin://domains: captured domains summary dataset.
License
This project is licensed under the MIT License.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
