io.github.coyaSONG/youtube-research
YouTube Research MCP
Citation-ready YouTube transcript research and optional channel intelligence for AI agents.
alive probed 2026-10-14
14tools
4.5ktokens in Claude Opus 5.5
4.7ktokens in Claude Code
2.3 %of a 200k context window
2.5ko200k_base estimate
2.6 sto initialize
20 msto list tools
- Run it
- npx -y @coyasong/youtube-mcp-server@2.0.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- YouTube Research MCP 1.2.0
- Capabilities
- prompts, resources, tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/coyaSONG/youtube-mcp-server
- Registry
- active, updated 2026-10-11 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| enhanced-transcript | 393 | 16 % |
| search-videos | 331 | 13 % |
| research-video | 281 | 11 % |
| get-video-comments | 248 | 10 % |
| get-segmented-transcript | 192 | 8 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.coyaSONG/youtube-research)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.