Primp MCP Server
An MCP server for the Primp HTTP client, enabling browser impersonation for requests and file uploads.
Primp MCP Server
A Model Context Protocol (MCP) server that provides access to the primp HTTP client library with browser impersonation capabilities.
Features
- Browser Impersonation: Impersonate various browsers (Chrome, Firefox, Safari, Edge) and operating systems
- HTTP Methods: Support for GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS
- Authentication: Basic auth and Bearer token support
- Proxy Support: HTTP/HTTPS proxy support
- File Uploads: Multipart form data file uploads
- Response Formats: Return responses as text, JSON, markdown, plain text, or rich text
- Advanced Options: Configurable timeouts, redirect handling, SSL verification
Installation
pip install -e .
Usage
The server provides two main tools:
1. primp_request
Make HTTP requests with browser impersonation (note, these instructions are for the LLM):
# Example usage in MCP client
{
"name": "primp_request",
"arguments": {
"url": "https://httpbin.org/get",
"method": "GET",
"impersonate": "chrome_131",
"impersonate_os": "windows",
"headers": {
"User-Agent": "My-App/1.0"
},
"return_format": "json"
}
}
2. primp_upload
Upload files using multipart form data:
# Example usage in MCP client
{
"name": "primp_upload",
"arguments": {
"url": "https://httpbin.org/post",
"files": [
{
"name": "file",
"filename": "example.txt",
"content": "SGVsbG8gV29ybGQ=", # base64 encoded
"content_type": "text/plain"
}
],
"data": {
"description": "Test upload"
}
}
}
Configuration
Add to your MCP settings:
{
"mcpServers": {
"primp": {
"command": "primp-mcp"
}
}
}
Supported Browsers
- Chrome (versions 99-131)
- Firefox (versions 99-133)
- Safari (versions 12-18, including iPad/iPhone)
- Edge (versions 99-131)
- OkHttp (versions 3.14.9-5.0.0)
Supported Operating Systems
- Windows
- macOS
- Linux
- Android
- iOS
License
MIT
関連サーバー
Bright Data
スポンサーDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Playwright MCP
Control a browser for automation and web scraping tasks using Playwright.
MCP Web Research Server
A server for web research that brings real-time information into AI models and researches any topic.
Jina Reader
Fetch the content of a remote URL as Markdown with Jina Reader.
HTTP Requests
An MCP server for making HTTP requests, enabling LLMs to fetch and process web content.
MCP RSS Crawler
Fetches and caches RSS feeds using a SQLite database for use with LLMs via the MCP protocol.
Playwright
Provides browser automation capabilities using Playwright. Interact with web pages, take screenshots, and execute JavaScript in a real browser environment.
Web Scraper Service
A Python-based MCP server for headless web scraping. It extracts the main text content from web pages and outputs it as Markdown, text, or HTML.
Intelligence Aeternum (Fluora MCP)
AI training dataset marketplace — 2M+ museum artworks across 7 world-class institutions with on-demand 111-field Golden Codex AI enrichment. x402 USDC micropayments on Base L2. First monetized art/provenance MCP server. Research-backed: dense metadata improves VLM capability by +25.5% (DOI: 10.5281/zenodo.18667735)
Douyin MCP Server
Extract watermark-free video links and copy from Douyin.
powhttp-mcp
MCP server enabling agents to debug HTTP requests better