Qdrant MCP Server for Vector Search and Semantic Memory
An official Qdrant MCP server implementation that provides semantic memory capabilities for AI agents. Enables storing and retrieving information using vector search, acting as a persistent knowledge layer on top of the Qdrant vector database.
What it does
Qdrant MCP Server for Vector Search and Semantic Memory
An official Qdrant MCP server implementation that provides semantic memory capabilities for AI agents. Enables storing and retrieving information using vector search, acting as a persistent knowledge layer on top of the Qdrant vector database.
Installation
Use the upstream install or setup path that matches your environment:
- docker build -t mcp-server-qdrant .
- docker run -p 8000:8000 \
- npx @smithery/cli install mcp-server-qdrant --client claude
- [
](https://insiders.vscode.dev/redirect/mcp/install?name=qdrant&config=%7B%2...
Requirements and caveats from upstream:
-
Using Docker
- necessary when running the server in a Docker container.
- The value of 'metadata' is a Python dictionary with strings as keys. \
Basic usage or getting-started notes:
-
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
-
| FASTMCP_SERVER_PORT | Port to run the server on | 8000 |
-
Using uvx
-
Extracted from upstream docs: https://raw.githubusercontent.com/qdrant/mcp-server-qdrant/HEAD/README.md
Source
Capabilities
Install
Quality
deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,457 chars)