turbopuffer
Search engine that combines vector search, full-text search, and filters on object storage. Bring your own API key from the turbopuffer dashboard.
Quick Start
# Connect this server (installs CLI if needed)
npx -y smithery mcp add turbopuffer
# Browse available tools
npx -y smithery tool list turbopuffer
# Get full schema for a tool
npx -y smithery tool get turbopuffer list
# Call a tool
npx -y smithery tool call turbopuffer list '{}'Direct MCP Connection
Endpoint: https://turbopuffer.run.tools
Required config:
bearerAuth(query) — Your turbopuffer API key. Create one at https://turbopuffer.com/dashboard.
Optional config:
region(query) — The turbopuffer region to use.
Tools (11)
list— List namespaces.schema.get— Get namespace schema.schema.update— Update namespace schema.metadata.get— Get metadata about a namespace.metadata.update— Update metadata configuration for a namespace.hint_cache_warm— Signal turbopuffer to prepare for low-latency requests.recall— Evaluate recall.write— Create, update, or delete documents.delete— Delete namespace.query— Query, filter, full-text search and vector search documents.explain_query— Explain a query plan.
# Get full input/output schema for a tool
npx -y smithery tool get turbopuffer