mcp-server-qdrant

Level ALocal

An official Qdrant Model Context Protocol (MCP) server implementation

Overview

An official Model Context Protocol server that acts as a semantic memory layer on top of the Qdrant vector search engine. It exposes two tools: qdrant-store for saving information with optional metadata, and qdrant-find for retrieving relevant content by query. It can connect to a remote Qdrant server or a local database, with configurable default collection, embedding model, and search result limit, plus a read-only mode. It works with any MCP-compatible client.

⭐ 1.6kDatabasePythonRepo ↗Updated 2026-11-20

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "qdrant-mcp-server-qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "COLLECTION_NAME": "<COLLECTION>"
      }
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/qdrant/mcp-server-qdrant

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "qdrant-mcp-server-qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "COLLECTION_NAME": "<COLLECTION>"
      }
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers