Skip to content
AI Dev Toolkit.
Esc
  • AI Token CounterCount tokens for GPT, Claude, Gemini, DeepSeek, Qwen and more.Tool
  • LLM API Cost CalculatorEstimate per-request, daily and monthly API costs.Tool
  • AI Model ComparisonCompare prices, context windows and features across models.Tool
  • AI Model Pricing PagesSpecs, real costs and cheaper alternatives for popular models.Tool
  • Context Window CheckerSee whether your text fits each model’s context window.Tool
  • Subscription vs API CalculatorFind out whether a chat plan or the API is cheaper for you.Tool
  • GPU / VRAM CalculatorCheck how much VRAM a local model needs and which GPUs fit.Tool
  • Prompt Caching CalculatorEstimate savings from prompt caching.Tool

MCP server · Databases

Qdrant MCP server

Gives an assistant a semantic memory: it stores notes in a Qdrant collection and finds them later by meaning rather than exact words.

Maintainer
Qdrant (official)
Licence
Apache-2.0
Runs
Locally (uvx)
Sign-in
Optional token
Last activity
2026-08-11

Overview

What it does

Qdrant’s official MCP server is a Python package run with uvx. It acts as a memory layer on top of the Qdrant vector database. One tool stores a piece of text with optional metadata, and the other searches the collection with a natural-language query. The server embeds text itself with a FastEmbed model, sentence-transformers/all-MiniLM-L6-v2 by default, so you do not need a separate embedding service.

You configure it with environment variables. Point QDRANT_URL at a Qdrant server or Qdrant Cloud with an API key, or use QDRANT_LOCAL_PATH for an embedded local database. It creates the collection if it does not exist. The tool descriptions can be rewritten, so the same server can act as a code-snippet store for Cursor or Windsurf. Choose it when you want an assistant to remember and recall information across sessions.

Tools

What the assistant can do

  • qdrant-store: save text and metadata to a collection
  • qdrant-find: semantic search over stored entries
  • Built-in FastEmbed embeddings
  • Local database path or remote Qdrant server
  • Read-only mode and custom tool descriptions

Install

Install Qdrant MCP server in your app

You need:

  • uv (provides uvx)
  • A Qdrant server or Qdrant Cloud cluster, or a local folder for embedded mode

Run in your project. --scope local keeps the servers private to you in this project; use user for every project.

Terminal
claude mcp add --env QDRANT_URL="${QDRANT_URL}" --env QDRANT_API_KEY="${QDRANT_API_KEY}" --env COLLECTION_NAME=your-collection-name --scope local qdrant -- uvx mcp-server-qdrant
Native Windows (PowerShell)
claude mcp add --env QDRANT_URL="$env:QDRANT_URL" --env QDRANT_API_KEY="$env:QDRANT_API_KEY" --env COLLECTION_NAME=your-collection-name --scope local qdrant -- uvx mcp-server-qdrant
  • Set QDRANT_URL, QDRANT_API_KEY first, e.g. export QDRANT_URL=… in your shell. The command saves the value, not the variable.

Want it alongside other servers? Open mcp-server-qdrant in the MCP config generator and add the rest; it writes one file per app. The snippets follow the setup in the server’s README, checked on 2026-10-14.

Before you install

  • qdrant-store writes to the collection and creates it if missing; set QDRANT_READ_ONLY=true to disable it.
  • Anything the assistant stores is kept in the vector database, so avoid storing secrets or personal data.
  • The first run downloads the embedding model.
  • A local MCP server runs with your user account’s permissions. Install it only from the source linked above. See how to choose a safe server.

Why it’s listed

Why we list it

The official Qdrant server and a simple, well-understood pattern for assistant memory.

Related

All MCP serversMCP config generatorGuide: MCP servers in Claude CodeGuide: what is MCP?