mcp-registry/mcp-server-qdrant

    ==================
      
       /// MCP ///
      /// MCP ///
        
    ==================
        
    [server:online]
    [protocol:ready]

mcp-server-qdrant

by qdrant

Official Model Context Protocol (MCP) server that uses Qdrant as a semantic-memory backend (vector store). It exposes two MCP tools – qdrant-store and qdrant-find – for persisting and retrieving embeddings.

808
114
Open Source
GitHubWebsiteDocumentationTwitterDiscord

01

qdrant-store

Store information (with optional metadata) in a specified Qdrant collection

02

qdrant-find

Retrieve relevant information from a Qdrant collection using a query

Installation

1. Prerequisites:
- Python 3.9+
- git
- (optional) running Qdrant instance – local docker: `docker run -p 6333:6333 -p 6334:6334 qdrant/qdrant`
2. Clone the repository
git clone https://github.com/qdrant/mcp-server-qdrant.git cd mcp-server-qdrant
3. Create and activate a virtual environment
python -m venv .venv source .venv/bin/activate # Windows: .venv\Scripts\activate
4. Install package and dependencies
pip install -U pip wheel pip install -r requirements.txt # or simply: pip install .
5. Configure environment (example)
export QDRANT_URL=http://localhost:6333 # Qdrant HTTP endpoint export QDRANT_API_KEY=your_api_key_if_needed # only if your Qdrant instance is protected export MCP_SERVER_HOST=0.0.0.0 # listening interface export MCP_SERVER_PORT=8000
6. Run the server
python -m mcp_server_qdrant # or: uvicorn mcp_server_qdrant.app:app --host $MCP_SERVER_HOST --port $MCP_SERVER_PORT
7. Verify
curl http://localhost:8000/healthz # should return OK

Documentation

License: Apache License 2.0
Updated 7/30/2025

Table of Contents