LanceDB vs Weaviate API + MCP

LanceDB

Embedded, no server, and tables can live directly in S3, GCS or Azure storage. No self-serve hosted API. Enterprise is sold through a contact form.

Weaviate API + MCP

Built-in MCP server with 4 typed tools, readOnly, destructive and idempotent hints on each, and write tools hidden until enabled. No public status page or incident history.

LanceDB

1. Use it through the Python or TypeScript library. There's no public endpoint an agent can call without an Enterprise deployment
2. Build an FTS index before calling query_type="hybrid", or hybrid search has no keyword side
3. Call optimize() after many small writes, since each write adds a new file version
4. Use select() to drop the vector column from results unless the task needs it
5. On object storage, set a read consistency interval if several processes write the same table

Weaviate API + MCP

1. Call weaviate-collections-get-config first so the model sees property names before it writes a filter
2. weaviate-query-hybrid defaults alpha to 0.75, so lower it for keyword-heavy queries
3. Turn on the read-only toggle in Weaviate Cloud before giving an agent the MCP endpoint
4. Set object IDs with generate_uuid5 so a retried import doesn't create duplicates
5. Free clusters hold one collection. Use tenants rather than extra collections