mcpField
R
Raccoon AI MCP Server

Raccoon AI MCP Server

Local
github.com/raccoonaihqBrowser Automation0Updated 85w ago
Repository

About Raccoon AI MCP Server

Raccoon AI MCP Server exposes Raccoon AI's LAM API for browser use, data extraction, and web task automation. It is for users of Claude Desktop or other MCP-compatible clients who need to navigate sites, gather structured information, or complete multi-step tasks.

Key features

  1. 01Search and browse websites
  2. 02Navigate interfaces and fill forms
  3. 03Extract data using defined schemas
  4. 04Automate multi-step website processes

Use cases

  1. 01Gather product details from shopping sites
  2. 02Find and summarize recent news articles
  3. 03Extract model or product details into a schema
  4. 04Research a topic across websites and prepare a report

MCP support

Exposes Raccoon AI LAM API capabilities to MCP-compatible clients, including web browsing, structured data extraction, and website task automation.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "raccoonai": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli"
      ]
    }
  }
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Raccoon AI MCP Server

smithery badge MCP Spec

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:

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.