Vidlens
VidLens MCP — video as a queryable local asset for AI agents. 47 tools across YouTube, social video URLs, local media, semantic search, transcription, and visual search.
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code (installable)
installable: each client documents how to load an MCP server of this type — that is the client's promise, not a claim verified against this capability
Work: Retrieval systems
Who it is for: AI engineer
Install (Claude Code):
claude mcp add vidlens -- npx -y vidlens-mcp- tashan score: 55.0
- Adoption: 147/wk
- Upkeep: 69.0
- Freshness: 89.0
- Evidence coverage: 100% of the inputs this score can use
- Health: active
Security audit
scanned 2026-08-09Every finding is shown in full — which advisory, the version that fixes it, and the exact command run at install time. Nothing in this audit is behind a licence.
node -e "console.log('\nVidLens MCP installed. Run: npx vidlens-mcp setup. Start the server with: npx vidlens-mcp serve. Docs: https://github.com/thatsrajan/vidlens-mcp\n')"npm ↗ · source ↗ · pkg:vidlens-mcp
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›
Measured 2026-08-09 · scorer s5 · how · something wrong here?