What it does
The Bangermap MCP server identifies YouTube outliers, meaning videos that beat their channel's own baseline. It exposes four tools: find_outliers ranks one channel's recent uploads by multiple, channel_baseline reports typical views, subscribers and uploads in the last 90 days, compare_channels lists the strongest outliers across several channels, and sweep_niche starts from a seed channel's featured channels and scores their outliers. A baseline is the median views of a channel's 30 most recent uploads of the same format that are at least 7 days old, with Shorts and long-form scored separately at 180 seconds. A video's multiple is its views divided by that baseline, and formats with fewer than 5 settled uploads are not scored.
It suits research into which videos overperformed for a given channel or niche, comparing channels against each other, or checking whether a single video is an outlier. Discovery follows the channel graph rather than keyword search. The repository also includes a skill that explains the method in the open Agent Skills format, and an n8n community node that uses the same operations.
Running it requires a free YouTube Data API key from the Google Cloud console, with YouTube Data API v3 enabled, supplied as YOUTUBE_API_KEY. The server communicates over stdio and can start without a key to inspect its tools. Requests go directly from the user's machine to googleapis.com, with no account or intermediary server. Each tool has a quota cost, and a free key provides 10,000 units a day, roughly 1,100 channel scans.
Limitations and requirements
Requires a free YouTube Data API key and a Google Cloud project with YouTube Data API v3 enabled. The free key provides 10,000 units per day; search calls cost 100 units each, and channel reads cost one unit. Formats with fewer than 5 settled uploads receive no baseline and are not scored. The repository is generated by a sync from a monorepo, so changes committed directly to it are overwritten on the next sync.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Bangermap
Find YouTube outliers, videos that beat their channel's own baseline, on your own free API key.
v1.0.3As shown on registry.modelcontextprotocol.io when we last read it