▌BestMCPTools.org
Qdrant MCP logo

Qdrant MCP

Semantic memory layer backed by the Qdrant vector database

Vector DatabaseOpen SourceClaude DesktopCursorVS CodeModerate✓ Verified
Visit Tool1,539 stars

Last verified: August 2, 2026

Own Qdrant MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

Active
Last code update: September 4, 2026License: Apache-2.0Checked September 28, 2026

How to Install Qdrant MCP

$uvx mcp-server-qdrant

Compatible with: Claude Desktop, Cursor, VS Code.

Setup by client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "qdrant-mcp": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "qdrant-mcp": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ]
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "qdrant-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ]
    }
  }
}

Claude Code (terminal)

claude mcp add qdrant-mcp -- uvx mcp-server-qdrant

Add any API keys or environment variables the server's README lists.

About Qdrant MCP

The official Qdrant MCP server turns the Qdrant vector database into a semantic memory layer for AI agents, letting them store and retrieve information by meaning. It's a lightweight way to add long-term, searchable memory or RAG to an agent, running locally or against a managed Qdrant Cloud cluster.

Qdrant MCP is a Vector Database MCP server designed for developers and AI power users. It enables extending AI assistants with real-world capabilities by exposing a structured set of tools over the Model Context Protocol. Key capabilities include standards-based mcp server interface, works with claude, gpt, gemini, and other mcp clients, tool discovery and structured outputs, and structured tool calls that work cleanly inside an LLM context. It integrates with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client, and is best suited for developers and AI power users who need ai engineers wiring assistants into real tools.

Key Features

  • vector database
  • semantic search
  • memory
  • RAG
  • Standards-based MCP server interface
  • Works with Claude, GPT, Gemini, and other MCP clients

Pricing

Open Source: from Free (self-hosted); Qdrant Cloud usage-based

Pros & Cons

Pros

  • Drop-in support across MCP-compatible AI clients
  • Reduces prompt boilerplate by exposing concrete tool calls
  • Active community and ongoing updates

Cons

  • Requires an MCP-capable client to use
  • Initial setup can require configuration
  • Capability surface depends on what the underlying service exposes

Best For

  • AI engineers wiring assistants into real tools
  • Teams adopting MCP as an integration standard
  • Power users who want more than chat

Our Take on Qdrant MCP

Qdrant MCP is an excellent open-source choice for giving agents durable semantic memory, with the flexibility to self-host for free or scale on Qdrant Cloud. Requires a bit of vector-store know-how, but it's fast, reliable, and cost-effective.

Frequently Asked Questions

Tags

#vector database#semantic search#memory#RAG