MCP For Claude Marketplace
LanceDB (Serverless Vector DB)

LanceDB (Serverless Vector DB) MCP Connector for Claude

A+

Manage vectorized data via LanceDB — perform similarity searches, create tables, and manage multi-modal embeddings.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your LanceDB Cloud account to any AI agent and take full control of your serverless vector storage and RAG infrastructure through natural conversation.

What you can do

  • Vector Orchestration — List all vectorized tables and retrieve precise schema metadata, including tensor dimensions and vector topologies directly from your agent
  • Similarity Search — Execute highly-optimized KNN (K-Nearest Neighbor) lookups to retrieve semantically related rows based on embedding array similarity
  • Dynamic Ingestion — Insert new structured row payloads and vectors into existing tables, updating the underlying ANN index in real-time
  • Table Management — Provision new columnar vector tables declaring specific Apache Arrow schemas and multi-dimensional layouts required for AI workloads
  • Database Audit — Discover active table boundaries and verify storage configurations assigned to your serverless database instance securely
  • Resource Cleanup — Irreversibly delete entire vector tables to maintain a clean and optimized data environment for your AI applications

How it works

  1. Subscribe to this server
  2. Enter your LanceDB API URL, API Key, and Database Name
  3. Start managing your vector storage from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • RAG Developers — perform semantic searches and verify document retrieval results through natural conversation without manual Python scripts
  • Data Engineers — provision and manage vector tables with strict Apache Arrow schemas to power multi-modal AI applications
  • AI Architects — monitor vector topologies and audit storage usage across multiple serverless database instances efficiently
vector-searchembeddingsragserverless-dbmulti-modaldata-indexing

6 tools expose this connector's capabilities to your AI agent.

get_table

Get precise schema and metadata for a specific LanceDB table

vector_search

Perform a highly-optimized KNN Vector similarity search

list_tables

List all vectorized tables residing in LanceDB

insert_rows

Data dynamically updates the underlying ANN index. Insert structured row payloads and vectors into a table

create_table

Provision a new LanceDB table with a strict schema

delete_table

Irreversibly vaporize an entire LanceDB vector table

See how to talk to your AI agent using LanceDB (Serverless Vector DB).

List all active tables in my LanceDB instance

I've retrieved your vector tables. Active tables include 'customer_docs', 'product_embeddings', 'support_kb', and 'user_logs'. Which one would you like to inspect the schema for?

Perform a vector search in 'product_embeddings' for this vector: [0.1, 0.2, ...]

Executing similarity search… I've found the 5 most relevant products. Highlights include 'Cloud-Native Sneakers' (Distance: 0.12), 'Edge Performance Runner' (Distance: 0.15), and 'Vector Pro Trainer' (Distance: 0.18). All results are now available in your workspace.

Show me the schema for the 'support_kb' table

Schema for 'support_kb': The table has 4 columns: 'id' (String), 'text' (String), 'vector' (Float32, Dimensions: 1536), and 'metadata' (JSON). It is currently using an IVF-PQ index for optimized ANN lookups.

Yes. Use the `vector_search` tool by providing the target Table name and a JSON array of floating-point numbers representing your query embedding. Your agent will return the k-nearest rows from LanceDB based on semantic similarity.

Related Connectors

GP

Glob Pattern Tester MCP

1 tools Official

Test whether a file path matches a glob pattern using the same algorithm used by npm and git. 130M+ weekly downloads.

A+ View details →
WB

World Bank Education & Health MCP

5 tools Official

Retrieve global life expectancy, infant mortality, literacy rates, and social welfare statistics without any authentication.

A+ View details →
HF

Hugging Face MCP

13 tools Official

Explore AI models, datasets and Spaces via Hugging Face — search models, inspect files, review discussions and track collections from any AI agent.

A+ View details →
JD

JWT Decoder & Verifier MCP

1 tools Official

Decode and mathematically verify JWT tokens local. Ensure API authentication tokens are cryptographically authentic and not expired.

A+ View details →