Leverages the LAM API for web browsing, data extraction, and complex web tasks automation.
Connect Raccoon AI to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Leverages the LAM API for web browsing, data extraction, and complex web tasks automation. The raccoon ai mcp server is what makes that connection.
Raccoon AI's Model Context Protocol (MCP) server that enables leveraging the LAM API for web browsing, data extraction, and complex web tasks automation.
Installation goes through your MCP client rather than a global install: point it at @smithery/cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Configuration is passed through the environment: RACCOON_SECRET_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
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
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. It is maintained by raccoonaihq; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Raccoon AI's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
{
"mcpServers": {
"raccoon-ai": {
"command": "npx",
"args": ["-y", "@smithery/cli"],
"env": {
"RACCOON_SECRET_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
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
| Variable | Description | Required |
|---|---|---|
| RACCOON_SECRET_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.