Knuckles-Team/vector-mcp

Vector MCP Server for AI Agents - Supports ChromaDB, Couchbase, MongoDB, Qdrant, and PGVector

Stars 15 Language Python Last updated 2026-06-29 Source on GitHub @Knuckles-Team

Install & configure

Install method detected from README: docker run

docker run -d \

Claude Desktop config snippet

Add to your claude_desktop_config.json (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "vector-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "vector-mcp[mcp]",
        "vector-mcp"
      ],
      "env": {
        "VECTOR_URL": "your_vector_url_here",
        "EMBEDDING_MODEL_ID": "your_embedding_model_id_here",
        "CHUNK_SIZE": "your_chunk_size_here",
        "VECTOR_API_KEY": "your_vector_api_key_here"
      }
    }
  }
}

View full README on GitHub

Why this is listed

This repository appears on MCP Servers Live because it matches the tracker's GitHub Search criteria (mcp-server) and was active in the recent indexing window. The tracker refreshes every 15 minutes, so the metadata above reflects the state at the most recent index pass. If the data here looks stale, the source repository may have been archived or moved out of the tracked topic; the next cron tick will reconcile.

Similar in this tracker

Explore by category