Qdrant MCP Server

Enables semantic search in Qdrant vector databases using OpenAI embeddings.

Local serverstdioPython 7

What is the Qdrant MCP server?

Qdrant MCP server exists for a simple reason — assistants are far more useful when they can act on Qdrant directly instead of describing what you should do. Enables semantic search in Qdrant vector databases using OpenAI embeddings.

What you get

This MCP server provides vector search capabilities using Qdrant vector database and OpenAI embeddings.

  • Semantic search in Qdrant collections using OpenAI embeddings
  • List available collections
  • View collection information

What the assistant can call

Once Qdrant is connected, these are the calls the assistant has available:

  • query_collection — Search a Qdrant collection using semantic search with OpenAI embeddings
  • list_collections — The list_collections tool exposed by this server
  • collection_info — The collection_info tool exposed by this server

Configuration and credentials

You will need 3 environment variables: OPENAI_API_KEY, QDRANT_URL, QDRANT_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python 3.10+ installed - Qdrant instance (local or remote) - OpenAI API key

Setting it up

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Qdrant's toolset — query_collection, list_collections, collection_info — is a fair guide to whether it matches your workflow. It is maintained by amansingh0311; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the qdrant mcp server does with a few real requests.

Available tools

ToolWhat it does
query_collectionSearch a Qdrant collection using semantic search with OpenAI embeddings.
list_collectionsThe list_collections tool exposed by this server.
collection_infoThe collection_info tool exposed by this server.

How to install the Qdrant MCP server

{
  "mcpServers": {
    "qdrant-openai": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "OPENAI_API_KEY": "your-value",
        "QDRANT_URL": "your-value",
        "QDRANT_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.10+ installed - Qdrant instance (local or remote) - OpenAI API key
VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
QDRANT_URLEndpoint or connection string the server talks to.Yes
QDRANT_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Qdrant to query collection.
  • Use Qdrant to list collections.
  • Use Qdrant to collection info.

Frequently asked questions

Yes! You can install it in Claude Desktop using the `mcp install` command, enabling semantic search within your Claude environment.