Qdrant MCP Server
About
The official Qdrant MCP server. Lets AI agents directly operate the Qdrant vector database: create and search collections, insert vector data, and perform semantic search — no manual API requests needed.
Our Verdict
Qdrant MCP Server brings database capabilities to the MCP ecosystem. Its GitHub popularity reflects community trust, and the standardized protocol ensures broad compatibility across AI clients.
Pricing
Use Cases
- Integrating database capabilities into AI agent workflows
- Building custom AI-powered tools with Qdrant MCP Server
- Enhancing AI agent functionality with standardized MCP access
Pros
- Qdrant MCP Server provides standardized MCP protocol access
- Open source with 1,485 GitHub stars
- Active development and community support
Cons
- Requires MCP-compatible client (Claude, Cursor, etc.)
- Setup complexity varies by client
- Some features may depend on client capabilities
Installation
uvx mcp-server-qdrantFrequently Asked Questions
What can Qdrant MCP do?
Lets AI agents directly operate the Qdrant vector database: create and manage collections, insert and update vector data, perform semantic similarity search, and manage indexes and filters. Ideal for building RAG (Retrieval-Augmented Generation) apps, semantic search, and recommendation systems.
Does Qdrant MCP need a Qdrant instance?
Yes, it needs a running Qdrant instance (either local Docker deployment or Qdrant Cloud). The MCP server connects via the Qdrant client API and requires the instance URL and API key (if applicable) to be configured.
Is Qdrant MCP free?
The MCP server itself is open source and free (Apache 2.0). Qdrant offers an open source version (self-hosted, free) and Qdrant Cloud (free tier available, usage-based billing beyond).