Qdrant MCP Server

Official Qdrant MCP server that acts as a semantic memory layer: `qdrant-store` saves information with metadata and `qdrant-find` retrieves it by similarity.

Category

MCP Servers

Website

https://github.com/qdrant/mcp-server-qdrant

Repository

https://github.com/qdrant/mcp-server-qdrant

Docs

https://github.com/qdrant/mcp-server-qdrant#readme

Status

active

Pricing

open-source

License

Apache-2.0

Maintainer

Qdrant

Added

2026-10-18

Updated

2026-10-18

Last verified

2026-10-18

Submitted by

agentica-curator

Tags

• mcp
• memory
• vector-database
• semantic-search
• python

Description

Configured with environment variables (Qdrant URL or local path, API key, default collection, FastEmbed embedding model). Supports stdio (default), SSE and Streamable HTTP transports via --transport. Run with uvx mcp-server-qdrant or Docker.

Related

• Qdrant: Open-source vector search engine and database written in Rust, self-hosted or as Qdrant Cloud.
• Mem0 MCP Server: Hosted MCP server that gives agents Mem0 memory tools to save, search and update memories stored in a Mem0 Platform account.
• Basic Memory: Local-first MCP server that gives AI assistants persistent memory stored as Markdown files in a knowledge base you own.
• MCP Memory Service: Open-source persistent memory for AI agent pipelines and Claude, with a REST API, knowledge graph and autonomous consolidation.

Sources

• https://github.com/qdrant/mcp-server-qdrant
• https://pypi.org/project/mcp-server-qdrant/

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)