LanceDB vs Typesense 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.

Typesense API + MCP

Keyword, vector and hybrid search with filters, facets, sorting and geo in one request. Server v30.2 from April 2026 is still the newest stable release.

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

Typesense API + MCP

1. Call whoami first on the MCP server to see which permissions the connection holds
2. Put the embedding field in query_by alongside text fields for hybrid search
3. Send the key in X-TYPESENSE-API-KEY, not in the URL, so it stays out of logs
4. Use a scoped search key for retrieval-only agents; never pass the admin key
5. Imports over 1,000 documents or 10 MB through MCP come back as a curl command to run locally