Skip to content
Agent Search Engine.
Submit a tool
Menu

Record · qdrant-mcp-sMCP serverCosts not checkedRecord checked Sep 23, 2026

Qdrant MCP Server

Qdrant's official MCP server: store and retrieve semantic memories in a Qdrant vector database.

Visit Qdrant MCP Server →View repository

Sources and review

Checked against public documentation on . Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.

Best for

Giving an assistant long-term semantic memory, or searching a code snippet library, backed by Qdrant.

About Qdrant MCP Server

Qdrant's official MCP server acts as a semantic memory layer on top of the Qdrant vector search engine, with tools to store information with optional metadata and to find relevant entries by meaning. It runs with uvx or Docker over stdio or SSE, and embeds text with a configurable FastEmbed model.

Qdrant MCP Server is listed in this index written primarily in Python, with 1.6k stars on GitHub. Its latest recorded repository push was in September 2026; that is not an ASE editorial review date.

Before connecting: access and data

This record's specific permissions have not been reviewed by ASE. Read the publisher's documentation before copying setup or connecting.

  • List the accounts, files and services the enabled tools can read, change or execute. Check your actual credentials and discovered tools.
  • Use narrowly scoped credentials and read-only mode where supported. Review proposed writes before approving them; a generated configuration does not apply these limits for you.
  • Local launch is not local-only data processing. External services receive requests, and your client may pass tool results to its model provider. Check both destinations before sharing private data.
  • Keep keys and browser session files out of shared config, repositories and screenshots. Know how to disconnect the server and separately revoke its credentials or account sessions.

Read the setup guide →

Add Qdrant MCP Server to your MCP client

Generated from the launch command in the project's README. Your client starts the server on demand.

Claude CodeRun in your terminal
claude mcp add qdrant-mcp-server -e QDRANT_URL=http://localhost:6333 -e COLLECTION_NAME=my-collection -- uvx mcp-server-qdrant
Cursor~/.cursor/mcp.json or .cursor/mcp.json
{
  "mcpServers": {
    "qdrant-mcp-server": {
      "command": "uvx",
      "args": ["mcp-server-qdrant"],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "COLLECTION_NAME": "my-collection"
      }
    }
  }
}
VS Code.vscode/mcp.json
{
  "servers": {
    "qdrant-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": ["mcp-server-qdrant"],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "COLLECTION_NAME": "my-collection"
      }
    }
  }
}
Claude Desktopclaude_desktop_config.json
{
  "mcpServers": {
    "qdrant-mcp-server": {
      "command": "uvx",
      "args": ["mcp-server-qdrant"],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "COLLECTION_NAME": "my-collection"
      }
    }
  }
}
Codex~/.codex/config.toml
[mcp_servers.qdrant-mcp-server]
command = "uvx"
args = ["mcp-server-qdrant"]
env = { QDRANT_URL = "http://localhost:6333", COLLECTION_NAME = "my-collection" }

Check the project's README for required accounts, keys and permissions before connecting. Setup guide for each client →

For agent buildersMake your product part of the discovery.Explore advertising