io.github.rajanrengasamy/vidlens-mcp
vidlens-mcp
YouTube intelligence layer for AI agents. 41 tools, 10 modules, zero config.
alive probed 2026-10-14
41tools
11ktokens in Claude Opus 5.5
11ktokens in Claude Code
5.4 %of a 200k context window
5.5ko200k_base estimate
561 msto initialize
7 msto list tools
- Run it
- npx -y vidlens-mcp@1.2.6 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- vidlens-mcp 0.3.0
- Capabilities
- 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/rajanrengasamy/vidlens-mcp
- Registry
- active, updated 2026-03-23 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| exploreYouTube | 560 | 10 % |
| searchVisualContent | 333 | 6 % |
| indexVisualContent | 326 | 6 % |
| importComments | 219 | 4 % |
| extractKeyframes | 216 | 4 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.rajanrengasamy/vidlens-mcp)
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.