Enables semantic search over personal markdown notes by indexing them into a vector database and exposing search, reindex, and status tools via MCP.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.QDRANT_URL— URL to the Qdrant instance (default: http://qdrant:6333).LITELLM_URL— URL to LiteLLM instance for embeddings (default: http://litellm:4000/v1).LITELLM_API_KEY— API key for embeddings (default: dummy).EMBEDDING_MODEL— Embedding model to use (default: text-embedding-3-small).COLLECTION_NAME— Qdrant collection name (default: notes_rag).VAULT_PATH— Default path to the markdown notes vault (default: /containers/productivity/obsidian/shared).CACHE_DB_PATH— Path to SQLite index cache DB (default: /app/data/index_cache.db).CHUNK_SIZE— Max characters per chunk (default: 1500).CHUNK_OVERLAP— Overlap between chunks (default: 200).[](https://m8ven.ai/mcp/spelech-notes-rag-mcp-11fmfw)