LLM + MCP Guide
This page focuses on the fastest path to value: connect, search, load only what you need, and answer with confidence.
1. Connect to Scribe MCP
Point your MCP client to Scribe and verify tool discovery.
list_tools()2. Find relevant transcriptions
Search before loading large records.
search_transcriptions(query: "roadmap", limit: 10)3. Load minimal context first
Use summary and metadata before segments.
get_transcription(id)Search first. Summary second. Segments last.
This keeps token usage low and response quality high.
1) search_transcriptions(query, limit)
2) get_transcription(id)
3) if needed: get_transcription_segments(id, skip, take)
4) stop when question is answeredSearch, load, segment, summarize
Create, link, export, collaborate
Directory and entity context
"Find the latest meeting where roadmap priorities were discussed, summarize decisions, and list explicit owners and deadlines. Use summaries first, then only load segments if needed."
The complete technical guide, examples, and edge cases are available in the repository docs.
Open LLM.md on GitHub