Weaviate
The MCP Server for Weaviate facilitates integration with Weaviate using a customizable Python-based server, enabling interaction with Weaviate databases and OpenAI APIs via configurable URL and API keys.
What is Weaviate?
Weaviate is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for weaviate facilitates integration with weaviate using a customizable python-based server, enabling interaction with weaviate databases and openai apis via configurable url and api keys....
The MCP Server for Weaviate facilitates integration with Weaviate using a customizable Python-based server, enabling interaction with Weaviate databases and OpenAI APIs via configurable URL and API keys.
This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The MCP Server for Weaviate facilitates integration with Wea
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-server-weaviateConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Weaviate
MCP Server Weaviate is a built-in MCP server embedded directly into Weaviate v1.37.1 and later, giving AI assistants native access to Weaviate's vector database through the Model Context Protocol. It exposes tools for inspecting collection schemas, listing multi-tenant tenants, performing hybrid vector and keyword searches, and upserting objects — all without deploying a separate sidecar process. This makes it straightforward for Claude and other LLM clients to query and populate a Weaviate knowledge base conversationally.
Prerequisites
- Weaviate v1.37.1 or later (self-hosted or Weaviate Cloud)
- MCP_SERVER_ENABLED=true environment variable set when starting Weaviate
- A Weaviate API key for authentication
- Claude Desktop or another MCP-compatible client that supports SSE or HTTP MCP transports
Enable the built-in MCP server
Set the MCP_SERVER_ENABLED environment variable to true before starting your Weaviate instance. The MCP endpoint will be available at /v1/mcp on the same port as the Weaviate REST API.
MCP_SERVER_ENABLED=true weaviate start
# or in docker-compose:
# environment:
# MCP_SERVER_ENABLED: "true"Obtain your Weaviate API key
For Weaviate Cloud, find your API key in the Weaviate Cloud Console. For self-hosted instances, configure API key authentication in your Weaviate configuration file and note the key.
Add the server to your MCP client config
Configure your MCP client to connect to the Weaviate MCP endpoint. The server uses Weaviate's existing API key authentication.
{
"mcpServers": {
"weaviate": {
"type": "http",
"url": "http://localhost:8080/v1/mcp",
"headers": {
"Authorization": "Bearer your_weaviate_api_key"
}
}
}
}Restart your MCP client
Save the configuration and restart Claude Desktop or your MCP client so it connects to the Weaviate MCP endpoint.
Verify tools are available
Ask Claude to list your Weaviate collections. If the server is reachable and authenticated, it will use the weaviate-collections-get-config tool and return your schema.
Weaviate Examples
Client configuration
MCP client config connecting to a local Weaviate instance with the MCP server enabled. Replace the URL with your Weaviate Cloud cluster URL if using Weaviate Cloud.
{
"mcpServers": {
"weaviate": {
"type": "http",
"url": "http://localhost:8080/v1/mcp",
"headers": {
"Authorization": "Bearer your_weaviate_api_key"
}
}
}
}Prompts to try
Use these prompts to search, inspect, and populate your Weaviate vector database through Claude.
- "List all collections in my Weaviate instance and show their schemas"
- "Search for documents about 'machine learning deployment' using hybrid search in the Articles collection"
- "List all tenants in the MultiTenantCollection"
- "Upsert a new object into the Products collection with name 'Widget A' and description 'A small widget'"
- "What properties does the BlogPost collection have?"Troubleshooting Weaviate
MCP endpoint returns 404 or connection refused
Verify that Weaviate v1.37.1 or later is running and MCP_SERVER_ENABLED=true is set. The endpoint is /v1/mcp on the same host and port as the REST API (default 8080). Check Weaviate logs for startup errors.
401 Unauthorized when connecting
Confirm the API key in your Authorization header matches a key configured in Weaviate's authentication settings. RBAC rules apply — ensure the key has the necessary permissions for the collections you are querying.
Hybrid search returns no results
Ensure the collection has data and that the vectorizer is configured. Hybrid search requires at least one vectorized property. Check the collection schema with weaviate-collections-get-config to confirm vectorizer settings.
Frequently Asked Questions about Weaviate
What is Weaviate?
Weaviate is a Model Context Protocol (MCP) server that mcp server for weaviate facilitates integration with weaviate using a customizable python-based server, enabling interaction with weaviate databases and openai apis via configurable url and api keys. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Weaviate?
Follow the installation instructions on the Weaviate GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Weaviate?
Weaviate works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Weaviate free to use?
Yes, Weaviate is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Weaviate Alternatives — Similar Databases Servers
Looking for alternatives to Weaviate? Here are other popular databases servers you can use with Claude, Cursor, and VS Code.
Excelize
★ 20.6kGo language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets
MCP Toolbox for Databases
★ 15.3kOpen source MCP server specializing in easy, fast, and secure tools for Databases.
DBHub
★ 2.8kA universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.
Tabularis
★ 2.1kA lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
Postgres AI Guide
★ 1.7kMCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
Anyquery
★ 1.7k🏎️ 🏠 ☁️ - Query more than 40 apps with one binary using SQL. It can also connect to your PostgreSQL, MySQL, or SQLite compatible database. Local-first and private by design.
Browse More Databases MCP Servers
Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Weaviate in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Weaviate?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.