MCP Server Weaviate
OfficialProvides integration with OpenAI's API, likely for embeddings or other AI capabilities when working with Weaviate
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Server Weaviatesearch for documents about machine learning"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Weaviate MCP server
This standalone server is deprecated. The Weaviate Model Context Protocol (MCP) server is now built into Weaviate itself — there is nothing to install or run separately.
Use the built-in MCP server
Weaviate ships an MCP server inside the main weaviate/weaviate binary, available as a preview from v1.37.1 onward. Enable it with a single environment variable:
MCP_SERVER_ENABLED=trueIt listens on the same port as the Weaviate REST API at /v1/mcp, authenticates via the existing API-key flow, and respects RBAC.
Tools exposed
Tool | Purpose |
| Inspect collection schemas |
| List tenants in a multi-tenant collection |
| Hybrid (vector + keyword) search |
| Create or update objects |
Documentation
Setup, environment variables, RBAC permissions, and per-tool reference: docs.weaviate.io/weaviate/configuration/mcp-server
The MCP standard: modelcontextprotocol.io
Weaviate repo (issues, feature requests): github.com/weaviate/weaviate
Related MCP server: Customized MCP Server
About this repository
Earlier versions of this repo contained a standalone Go implementation of an MCP server that wrapped the Weaviate REST API. That implementation has been superseded by the built-in server and is no longer maintained. The history is preserved in git for reference; for the previous source, see the commits before this notice.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/weaviate/mcp-server-weaviate'
If you have feedback or need assistance with the MCP directory API, please join our Discord server