Qdrant

by qdrant · Databases · mcp-server, ai, pypi

Store and retrieve vector-based memories for AI systems.

This MCP server, developed by Qdrant, provides a semantic memory layer on top of the Qdrant vector database. Built for use with Claude Desktop, it offers tools for storing and retrieving memories using Qdrant's vector search capabilities. The server leverages FastEmbed models for encoding memories, with the default being 'sentence-transformers/all-MiniLM-L6-v2'. Key features include automatic collection creation, configurable embedding models, and support for both command-line and environment variable configuration. By integrating AI capabilities with Qdrant's efficient vector search, this implementation enhances semantic memory retrieval for AI assistants. It is particularly useful for scenarios requiring persistent memory storage, semantic similarity search, and scalable vector operations in AI applications.

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

Install

uvx mcp-server-qdrant

Tags: mcp-server, ai, pypi

⭐ 1,298 GitHub stars · Source: pulsemcp

About Databases MCP servers and Claude skills

Databases MCP servers extend what AI agents can do inside Claude Code, Cursor, Copilot, Codex, and Windsurf. The Skiln directory indexes 16,000+ such integrations across 22 categories.

Qdrant is one of hundreds of Databases entries indexed on Skiln. Browse the full Databases category or the complete directory of Claude skills, MCP servers, agents, commands, and hooks.

Related Databases MCPs and skills

  • Snowflake by snowflake-labs

    Bridges AI applications with Snowflake's data platform for database interaction

  • Ultra (Multi-AI Provider) by realmikechong

    Unified server providing access to OpenAI O3, Google Gemini 2.5 Pro, and Azure OpenAI models with automatic usage tracking, cost estimation, and nine specialized development tools for code analysis, debugging, and documentation generation.

  • SQL Server Performance Monitor by erikdarlingdata

    SQL Server performance monitoring with DuckDB storage and natural language queries for CPU, wait stats, blocking, query performance, memory, and I/O.

  • Paelladoc by jlcases

    Generates structured documentation for software projects through code analysis, template management, and specialized commands for consistent documentation practices across diverse project types.

  • Skylos by duriantaco

    Privacy-first SAST tool for Python, TypeScript, and Go that detects dead code, security vulnerabilities, and code quality issues with hybrid AST and optional LLM analysis.

  • Claude Recall by nhevers

    Persistent memory system for Claude Code that automatically captures session context, stores observations in SQLite with vector search, and injects relevant history into future coding sessions to maintain continuity across development workflows.

  • Airtable by domdomegg

    Provides read and write access to Airtable databases.

  • MotherDuck & DuckDB by motherduckdb

    Integrates MotherDuck and local DuckDB databases for flexible querying and analysis of structured data in MCP-compatible environments.

Frequently asked questions

How do I install Qdrant?

Add the install command above to your Claude Code, Cursor, or Windsurf MCP configuration. Most servers register via npx, a local command, or a Docker image. Refer to the source repository for environment variables and credential requirements.

Which clients support Qdrant?

Any MCP-compatible client works: Claude Desktop, Claude Code CLI, Cursor, Windsurf, Zed, and VS Code with the official MCP extension. OpenAI Codex and GitHub Copilot increasingly support MCP via adapter bridges.

Is Qdrant free?

The server itself is typically open source. Any upstream service (API keys, paid tiers, hosted infrastructure) may have its own pricing. Check the source repository for details.