Qdrant

MCP server by Qdrant

Store and retrieve semantic memories in a Qdrant vector database collection.

Runs locally (Runs on your machine: its page has the install command)Runs with uvx

Install Qdrant

Runs on your machine. Your client starts it with this command:

uvx mcp-server-qdrant

Needs uv (Python) on your computer. The setup steps below show where the command goes in each client.

  • QDRANT_URL Qdrant server URL (or set QDRANT_LOCAL_PATH for local storage).
  • COLLECTION_NAME Default collection name.

Share this server

Opens this page, with the install command and setup steps.

mcp.tc/i/qdrant

About

Connects an assistant to a Qdrant vector search engine and uses it as a semantic memory layer. It can store pieces of information with optional metadata and later retrieve relevant entries by natural language query. Embeddings are created with FastEmbed models, with sentence-transformers/all-MiniLM-L6-v2 as the default.

Runs locally with uvx mcp-server-qdrant over stdio by default; SSE and streamable HTTP transports and a Docker image are also available. Configure it with QDRANT_URL or QDRANT_LOCAL_PATH plus COLLECTION_NAME. QDRANT_API_KEY is only needed for Qdrant Cloud or secured servers. A missing collection is created automatically.

What you can do

  • Store information with optional JSON metadata in a Qdrant collection
  • Retrieve relevant stored entries with a natural language query
  • Use a default collection or pass a collection name per call
  • Run against a Qdrant server, Qdrant Cloud or a local database path
  • Choose the FastEmbed embedding model through an environment variable

Tools

Local servers list their tools once they’re running, and this one doesn’t publish its list in advance. Your client shows them after you add it.

Example prompts

  • Remember that our staging database runs on port 5433.

  • Search my memory for notes about the payment service design.

  • Store this code snippet with metadata describing what it does.

  • Find what I saved earlier about deployment steps.

Set up

Every client starts Qdrant on your machine with the same command. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio qdrant --env "QDRANT_URL=<YOUR_QDRANT_URL>" --env "COLLECTION_NAME=<YOUR_COLLECTION_NAME>" -- uvx mcp-server-qdrant
  1. Start Claude Code and type /mcp. qdrant should show as connected.

Add --scope user to make it available in every project. Replace the placeholders with your own values.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ],
      "env": {
        "QDRANT_URL": "<YOUR_QDRANT_URL>",
        "COLLECTION_NAME": "<YOUR_COLLECTION_NAME>"
      }
    }
  }
}
  1. Save the file and restart Claude Desktop. Replace the placeholders with your own values.

Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ],
      "env": {
        "QDRANT_URL": "<YOUR_QDRANT_URL>",
        "COLLECTION_NAME": "<YOUR_COLLECTION_NAME>"
      }
    }
  }
}

Needs uv (Python) on your computer. Replace the placeholders with your own values.

VS Code

Or from a terminal:

code --add-mcp '{"name":"qdrant","type":"stdio","command":"uvx","args":["mcp-server-qdrant"],"env":{"QDRANT_URL":"<YOUR_QDRANT_URL>","COLLECTION_NAME":"<YOUR_COLLECTION_NAME>"}}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "qdrant": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ],
      "env": {
        "QDRANT_URL": "<YOUR_QDRANT_URL>",
        "COLLECTION_NAME": "<YOUR_COLLECTION_NAME>"
      }
    }
  }
}

Needs uv (Python) on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ],
      "env": {
        "QDRANT_URL": "<YOUR_QDRANT_URL>",
        "COLLECTION_NAME": "<YOUR_COLLECTION_NAME>"
      }
    }
  }
}
  1. Refresh the MCP server list in Cascade. Replace the placeholders with your own values.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add qdrant --env "QDRANT_URL=<YOUR_QDRANT_URL>" --env "COLLECTION_NAME=<YOUR_COLLECTION_NAME>" -- uvx mcp-server-qdrant

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.qdrant]
command = "uvx"
args = ["mcp-server-qdrant"]
env = { QDRANT_URL = "<YOUR_QDRANT_URL>", COLLECTION_NAME = "<YOUR_COLLECTION_NAME>" }

Needs uv (Python) on your computer. Replace the placeholders with your own values.

Gemini CLI

gemini mcp add -e "QDRANT_URL=<YOUR_QDRANT_URL>" -e "COLLECTION_NAME=<YOUR_COLLECTION_NAME>" qdrant uvx mcp-server-qdrant

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ],
      "env": {
        "QDRANT_URL": "<YOUR_QDRANT_URL>",
        "COLLECTION_NAME": "<YOUR_COLLECTION_NAME>"
      }
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs uv (Python) on your computer. Replace the placeholders with your own values.

FAQ

Can I paste mcp.tc/i/qdrant into my MCP client?

No. Qdrant runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx mcp-server-qdrant.

Does Qdrant need an API key?

No. It reads QDRANT_URL and COLLECTION_NAME from its environment; the setup steps show where to set them.

Is Qdrant a remote or a local server?

Local. Your client starts it as a process on your computer with uvx mcp-server-qdrant, which needs uv (Python).

What can Qdrant do?

You can store information with optional JSON metadata in a Qdrant collection, retrieve relevant stored entries with a natural language query and use a default collection or pass a collection name per call.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Who wrote this page?

mcp.tc’s robot read Qdrant’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

Embed

Show Qdrant in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work

README badge

Badge preview, lightBadge preview, dark
Markdown
[![Qdrant on mcp.tc](https://mcp.tc/i/qdrant/badge.svg)](https://mcp.tc/i/qdrant)
HTML
<a href="https://mcp.tc/i/qdrant"><img src="https://mcp.tc/i/qdrant/badge.svg" alt="Qdrant on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/qdrant.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/qdrant" title="Qdrant on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/qdrant.json

What each field means

mcp.tc isn’t affiliated with Qdrant. This page was built from Qdrant’s public metadata, last checked on 3 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.