MCP Rquest

A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.

python

43

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "xxxbrian-mcp-rquest": {
      "command": "uvx",
      "args": [
        "mcp-rquest"
      ]
    }
  }
}

This MCP server implements a Model Context Protocol setup for advanced HTTP interactions and document processing, enabling realistic browsing-like requests and easy conversion of HTML/PDF content into Markdown for large language models.

How to use

Set up a local MCP server and connect a client to perform HTTP-like actions through a controlled interface. You can use the server to fetch web content, submit forms, handle JSON or multipart payloads, and convert HTML or PDF responses into Markdown for easier processing by LLMs. Start the local MCP server with one of the provided runtime commands and point your client to the corresponding interface.

How to install

Prerequisites: Python installed (for Python-based startup), or a runtime that can run uvx/uvy based commands. You will install the MCP package and then run it using one of the supported runtime commands.

# Install with uvx-based runtime (recommended for direct execution)
# No extra setup beyond installing uvx integration

# Install with pip
pip install mcp-rquest

# Run via module entry point
python -m mcp_rquest

Additional sections

Configuration for Claude.app and similar clients allows you to choose a startup method that fits your environment. You can run the MCP server locally as a standard stdio service or connect through an HTTP endpoint if you host a remote MCP instance.

Available tools

http_get

Perform GET requests with optional parameters to fetch resources from the web.

http_post

Submit data via POST requests, including JSON payloads and form data.

http_put

Update resources with PUT requests and manage resource state.

http_delete

Remove resources via DELETE requests.

http_patch

Partially update resources with PATCH requests.

http_head

Retrieve only headers from a resource to inspect metadata.

http_options

Retrieve available options for a resource to understand capabilities.

http_trace

Diagnostic request tracing to debug interactions.

get_stored_response

Retrieve stored large responses, optionally by line range.

get_stored_response_with_markdown

Convert stored HTML or PDF responses to Markdown for better processing by LLMs.