What prerequisites are needed?
Python 3.8 or higher, an MCP-compatible client like Claude Desktop, and your Raccoon AI Secret Key and Passcode.
@raccoonaihq
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"raccoonai-mcp-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"install",
"@raccoonaihq/raccoonai-mcp-server",
"--client",
"claude"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Raccoon AI MCP Server is a Model Context Protocol server that integrates with Raccoon AI's LAM API to enable web browsing, data extraction, and complex web task automation for MCP-compatible clients like Claude Desktop.
Install via Smithery or from source using uv pip install -e ., then configure with your Raccoon AI Secret Key and Passcode via mcp install src/raccoonai_mcp_server/server.py -v RACCOON_SECRET_KEY=... -v RACCOON_PASSCODE=.... Invoke web tasks using natural language prompts in Claude Desktop.
Python 3.8 or higher, an MCP-compatible client like Claude Desktop, and your Raccoon AI Secret Key and Passcode.
Install via Smithery (`npx -y @smithery/cli@latest install @raccoonaihq/raccoonai-mcp-server`) or from source, then run `mcp install` with your credentials.
Your Secret Key and Passcode are available at [https://platform.flyingraccoon.tech](https://platform.flyingraccoon.tech).
You can search websites, fill forms, extract structured data, and automate multistep workflows such as product research or news aggregation.
Yes, it uses Raccoon AI’s LAM API, which handles browser automation and data extraction in the cloud.
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
不止于 CSS
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

Model Context Protocol Servers

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
评论