Weaviate MCP

Runs similarity and hybrid queries against a Weaviate instance: classes, properties, and returned objects. It is the retrieval half of a RAG stack, and the same warning applies — retrieval returns candidates, not answers.…

Community stdio Verified 2026-11-20 databasevectorragsearch

Use it for

Searching a self-hosted vector index from an agent

Skip it if

Index management as a routine agent action

What it is

Runs similarity and hybrid queries against a Weaviate instance: classes, properties, and returned objects. It is the retrieval half of a RAG stack, and the same warning applies — retrieval returns candidates, not answers. The namespace or class scope belongs in the tool configuration, not the prompt.

Install

Terminal
uvx weaviate-mcp

Client configuration

Paste this into your MCP client config, then restart the client.

MCP client config (JSON)
{
  "mcpServers": {
    "avbbc": {
      "command": "npx",
      "args": ["-y", "uvx weaviate-mcp"]
    }
  }
}

Overlapping servers

All servers
  • 01
    Chroma MCPCommunity

    Queries a Chroma collection locally, with metadata filters. It is the easiest vector store to stand up for a prototype: no server, no cloud account, and the same que…

    #database#vector#local
    Pythonstdio
  • 02
    Milvus MCPCommunity

    Queries Milvus collections and returns matching entities with scores and metadata. It exists for teams that already run Milvus at scale; the tool is thin by design a…

    #database#vector#search
    Pythonstdio
  • 03
    PlanetScale MCPCommunity

    Reads PlanetScale databases and branches, and can run SQL against a branch. The branching model is the safety feature: point the agent at a branch, let it experiment…

    #database#mysql#schema
    TypeScriptstdio

Tools that use this server

All tools

Skills built around it

All skills