orange-raccoonai-mcp-server 0.0.1

A MCP server for Raccoon AI LAM API

Raccoon AI MCP Server

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

What can you do with this?

• Search and browse websites
• Fill out forms and navigate UI elements
• Extract structured data based on defined schemas
• Handle multistep processes across websites

Prerequisites

Before using the Raccoon LAM MCP server, you'll need:

• Python 3.8 or higher
• Claude Desktop or another MCP-compatible client
• Raccoon AI Secret Key and your Raccoon Passcode

Installation

Using Smithery

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

From source

git clone https://github.com/raccoonaihq/raccoonai-mcp-server.git

cd raccoonai-mcp-server

uv pip install -e .

To configure in Claude Desktop

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

Replace <RACCOON_SECRET_KEY> and <RACCOON_PASSCODE> with your actual creds. You can find them here.

Examples

Here are some example prompts that can be used with Claude to perform a variety of web tasks:

1. Can you extract product information from Amazon.com for the top-rated gaming keyboards?
2. Find and summarize the latest news articles about renewable energy technologies.
3. Find the 3 latest iPhone models and extract the details in a schema.
4. Do a deepsearch and generate a detailed report on Small Language Models.

Documentation

For more information, refer to:

• Raccoon LAM API Documentation
• Model Context Protocol Documentation