Weaviate

Weaviate MCP Connector for Claude

A+

Search and manage vector data on Weaviate — the AI-native database for building production-grade AI applications.

7 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Weaviate instance to any AI agent and harness the power of vector search and semantic data management through natural conversation.

What you can do

  • Semantic Search — Perform nearest neighbor vector similarity searches to find relevant content based on context and meaning
  • Schema Management — Retrieve the complete instance schema or specific class definitions to understand your data structure
  • Object Discovery — Browse and list data objects within any class, including full property values and vector data
  • Deep Data Audit — Retrieve specific data objects by their UUID to inspect metadata and internal configurations
  • Cluster Monitoring — Monitor operational health, node status, and resource usage of your Weaviate cluster nodes
  • Instance Metadata — View server version, enabled modules, and high-level configuration details directly from your agent

How it works

  1. Subscribe to this server
  2. Enter your Weaviate Base URL and API Key
  3. Start querying your vector data collections through Claude, Cursor, or any MCP-compatible client

No more manual JSON querying in complex database consoles. Your AI agent becomes your vector database administrator.

Who is this for?

  • AI Developers — test and refine semantic search queries and verify vector data ingestion
  • Data Engineers — audit database schemas, monitor cluster health, and browse indexed objects
  • Research Teams — quickly surface relevant documents and data points from massive vector collections through chat
  • SRE & DevOps — monitor the operational status of Weaviate nodes and manage instance configurations
semantic-searchvector-embeddingsschema-managementnearest-neighborai-nativedata-indexing

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

get_class_schema

Retrieves the schema definition for a specific class (collection)

get_instance_metadata

Retrieves metadata about the Weaviate instance

get_cluster_nodes

Retrieves operational information about the Weaviate cluster nodes

get_object_details

Retrieves a specific data object by its UUID

get_full_schema

Retrieves the complete Weaviate schema (all collections)

list_objects

Supports basic pagination via limit. Lists data objects within a specific class

search_near_vector

Provide a class name and a query vector as a JSON array of floats. Performs a nearest neighbor vector similarity search

See how to talk to your AI agent using Weaviate.

List all classes in my Weaviate schema.

I found 3 classes in your schema: 'Article', 'Product', and 'UserFeedback'. Would you like to see the property definitions for any of these classes?

Search the 'Article' class for items similar to this vector: [0.12, -0.05, 0.88, ...].

I found 5 similar articles. The top match is 'Vector Search for Beginners' (UUID: 550e8400-e29b...) with a similarity score of 0.94. Would you like to see the full content of this article?

What is the current health status of my Weaviate cluster nodes?

All 3 nodes in your cluster are currently 'HEALTHY'. Node-1 is using 42% CPU and 6.5GB RAM. Node-2 and Node-3 are also within normal operating parameters. No issues detected.

Yes. The `search_near_vector` tool allows you to perform semantic searches by providing a query vector as a JSON array of floats. Your AI agent will return the most similar objects from your Weaviate collection.

Related Connectors