Bangermap is a Model Context Protocol (MCP) server: Find YouTube outliers, videos that beat their channel's own baseline, on your own free API key. In practice that means any MCP-compatible AI assistant can call Bangermap's tools directly — the model decides when to use them in a conversation or agent run.
It runs locally: the npm package bangermap-mcp speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need YOUTUBE_API_KEY. The current release is v1.0.3, published under the MIT license, with source at AdesiaHQ/bangermap-integrations on GitHub.
Bangermap is listed under Development on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Bangermap for AdesiaHQ, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
▸npm package — bangermap-mcp · MCP over stdio
▸Credentials — Requires YOUTUBE_API_KEY
▸Open source — MIT license · AdesiaHQ/bangermap-integrations