Back to code-only MCP servers

PocketRAG

updated this year

PocketRAG is a zero-infrastructure, portable agent plugin (Skill + FastMCP Server) that turns NotebookLM Enterprise (via Vertex AI Discovery Engine) into an instant, managed RAG backend for any LLM client (Claude Desktop, Cursor, Gemini, Cline). Bring your own documents to your AI assistant in under 60 seconds.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository
github.com/mbettan/PocketRAG
License
Apache-2.0
Last update
2026-06-18
GitHub stars
★ 0
Homepage
mbettan.github.io/PocketRAG/

Listed in

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.