raccoonai-mcp-server

raccoonai-mcp-server

3.2

Raccoon AI's Model Context Protocol (MCP) server enables leveraging the LAM API for web browsing, data extraction, and complex web tasks automation.

The Raccoon AI MCP Server is a powerful tool designed to facilitate web browsing, data extraction, and automation of complex web tasks using the LAM API. It is compatible with the Model Context Protocol, allowing seamless integration with various MCP-compatible clients like Claude Desktop. Users can perform tasks such as searching and browsing websites, filling out forms, navigating UI elements, extracting structured data, and handling multistep processes across different websites. The server requires Python 3.8 or higher and specific credentials, including a Raccoon AI Secret Key and Passcode, to operate. Installation can be done via Smithery or directly from the source, and it can be configured to work with Claude Desktop for enhanced functionality.

Features

  • Web Browsing: Search and browse websites efficiently.
  • Form Automation: Fill out forms and navigate UI elements automatically.
  • Data Extraction: Extract structured data based on defined schemas.
  • Multistep Process Handling: Manage complex processes across multiple websites.
  • MCP Compatibility: Seamless integration with MCP-compatible clients like Claude Desktop.

Usage with Different Platforms

smithery

bash
npx -y @smithery/cli@latest install @raccoonaihq/raccoonai-mcp-server --client claude

source

bash
git clone https://github.com/raccoonaihq/raccoonai-mcp-server.git
cd raccoonai-mcp-server
uv pip install -e .

claude_desktop

bash
mcp install src/raccoonai_mcp_server/server.py -v RACCOON_SECRET_KEY=<RACCOON_SECRET_KEY> -v RACCOON_PASSCODE=<RACCOON_PASSCODE>