Happy slice of mcp pizzaMCP.pizza

mcp-server-qdrant

MCP.Pizza Chef: qdrant

Two simple actions do all the work: one stores a piece of text with optional labels, the other finds whatever comes closest in meaning to what you asked. Because it matches on meaning rather than exact words, something filed months ago still surfaces from a vague description. It runs against a Qdrant search engine you host yourself or use in the cloud, and a read-only setting stops anything new being saved.

Data
Notes

Use This MCP server To

Save useful facts my assistant can recall later Search my saved notes by meaning, not exact wording Build a knowledge store my assistant can draw on Keep project decisions where I can find them again Look something up without remembering the exact phrase

README

mcp-server-qdrant: A Qdrant MCP server

smithery badge

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Overview

An official Model Context Protocol server for keeping and retrieving memories in the Qdrant vector search engine. It acts as a semantic memory layer on top of the Qdrant database.

Components

Tools

  1. qdrant-store
    • Store some information in the Qdrant database
    • Input:
      • information (string): Information to store
      • metadata (JSON): Optional metadata to store
      • collection_name (string): Name of the collection to store the information in. This field is required if there are no default collection name. If there is a default collection name, this field is not enabled.
    • Returns: Confirmation message
  2. qdrant-find
    • Retrieve relevant information from the Qdrant database
    • Input:
      • query (string): Query to use for searching
      • collection_name (string): Name of the collection to store the information in. This field is required if there are no default collection name. If there is a default collection name, this field is not enabled.
    • Returns: Information stored in the Qdrant database as separate messages

Environment Variables

Configuration is done via environment variables. The only command-line argument is --transport, used to select the transport protocol.

Note

You cannot provide both QDRANT_URL and QDRANT_LOCAL_PATH at the same time.

mcp-server-qdrant FAQ

Which apps work with it?
Claude Desktop, Cursor, VS Code, and Windsurf all have documented setups, plus a one-command install through Smithery.
Do I need a key?
For the hosted Qdrant cloud, yes. Running it locally or against a file on your own disk needs no key.
Can I use this to remember things between conversations?
Yes — that is the whole point. Anything saved stays available to later chats.
Can I stop it saving anything new?
Yes. A read-only setting removes the save action and leaves only search.
How hard is the setup?
It leans technical: run or sign up for the search engine, set a handful of values, then paste in the configuration.
Does it need an internet connection?
Not necessarily. It can run entirely on your own machine against a local database file.