MCP ServerSTDIO

Qdrant MCP Server

Qdrant’s official MCP server takes the opposite approach to most database servers: instead of exposing the API surface, it exposes two tools. Store something with its metadata, and find things semantically similar to a query. Embedding happens inside the server, so the agent never handles a vector.

Hosted URL

Bring your own

Suggested model

Claude Sonnet 4.5

Chat with 60+ AI models on the same workflow — switch to a different model mid-conversation and re-run the same prompt, or use Compare mode to put several side-by-side and balance quality vs. cost.

Auth

A Qdrant URL and API key for Cloud or a remote instance. Neither is needed if you run against a local on-disk path.

What the Qdrant MCP server does

How models use it and what it is built for.

The server is built as a semantic memory layer rather than a database client. qdrant-store takes a piece of text plus optional structured metadata, embeds it with the configured model and writes it to a collection. qdrant-find takes a natural-language query, embeds it the same way and returns the closest matches with their metadata attached. That is the whole surface, and the narrowness is the point — a model picks correctly between two well-described tools far more reliably than between twenty. The detail that makes it genuinely flexible is that both tool descriptions are configurable by environment variable. Rewriting them turns the same server into a code-snippet memory, a decisions log or a support-ticket search, because the description is what the model reads when deciding whether to call it. It runs over stdio via uvx, or in SSE mode when you want to host it centrally, and can point at Qdrant Cloud, a self-hosted instance or a local on-disk path with no server at all.

Tools the Qdrant MCP server exposes

Typical tools an AI model can call. Exact names vary by version.

  • qdrant-store — embed a piece of text with optional metadata and store it in a collection
  • qdrant-find — semantic search by natural-language query, returning matches and metadata
  • TOOL_STORE_DESCRIPTION / TOOL_FIND_DESCRIPTION — rewrite what the model reads about each tool
  • EMBEDDING_MODEL — swap the model used for both writing and querying
  • QDRANT_LOCAL_PATH — run entirely on local disk with no Qdrant server

Connecting to Qdrant

Taken from the official Qdrant documentation — see qdrant/mcp-server-qdrant — official repository for the full reference.

Environment variables

  • QDRANT_URL

    URL of the Qdrant instance, e.g. https://xyz.cloud.qdrant.io:6333. Omit if using QDRANT_LOCAL_PATH.

  • QDRANT_API_KEY

    API key for Qdrant Cloud or a secured self-hosted instance.

  • COLLECTION_NAMErequired

    Collection to read and write. Created automatically if it does not exist.

  • EMBEDDING_MODEL

    FastEmbed model name. Defaults to sentence-transformers/all-MiniLM-L6-v2.

  • QDRANT_LOCAL_PATH

    Local directory for an embedded instance. Mutually exclusive with QDRANT_URL.

  • TOOL_FIND_DESCRIPTION

    The description the model reads for the find tool. Rewriting this is how you specialise the server.

Client configuration

uvx against Qdrant Cloud

The collection is created on first write if it does not already exist.

{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": ["mcp-server-qdrant"],
      "env": {
        "QDRANT_URL": "https://xyz.cloud.qdrant.io:6333",
        "QDRANT_API_KEY": "YOUR_API_KEY",
        "COLLECTION_NAME": "agent-memory"
      }
    }
  }
}

Local on-disk, no server

Good for a single-machine setup or trying the server out. Not suitable for concurrent clients.

{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": ["mcp-server-qdrant"],
      "env": {
        "QDRANT_LOCAL_PATH": "/path/to/qdrant-data",
        "COLLECTION_NAME": "agent-memory"
      }
    }
  }
}

Example prompts to try

Copy any of these into MCP Agent Studio after connecting.

  • Remember this debugging approach and why it worked, tagged with the service name.

  • Have we solved something like this connection-pool error before?

  • Store this architecture decision with its date and the alternatives we rejected.

  • Find the three most relevant past incidents to what is happening now.

Models on MCP Playground

This is not a single-model product: you get the same MCP connection with 60+ models (Claude, GPT, Gemini, DeepSeek, open-weight, and more), you can switch mid-conversation, and you can open Compare mode to run the same prompt against multiple models at once. The card above is a suggested starting point for this server — not the only choice.

Default pick for Qdrant

Claude Sonnet 4.5

Retrieval quality depends on the model writing a good query and judging which results are actually relevant. Sonnet 4.5 discards weak matches instead of citing them.

Check an AI agent can actually use the Qdrant MCP server

Listing tools proves the server is reachable, not that a model can work with it. Evals go further: they read every tool on the server, write a test suite from its real schemas, and run it — code decides pass/fail on the responses (schema conformance, error codes, pagination, result caps) while a scoring model grades plain-English tasks driven through the tools.

Get a pass/fail report per tool with the evidence behind each verdict — and replay the same suite after every schema change. Destructive tools are excluded from the run.

Run evals

Try the Qdrant MCP server in your browser

Open MCP Agent Studio with the connection pre-filled. Add your token, pick any of 60+ models, and start chatting — no install required.

Open Agent Studio

Qdrant MCP server — FAQ

Common questions about connecting, scoping and using it safely.

What is the Qdrant MCP server?

It is Qdrant’s official MCP server, a semantic memory layer over a Qdrant collection. It exposes two tools — qdrant-store and qdrant-find — and handles embedding internally, so the agent works in plain text.

Do I have to generate embeddings myself?

No. The server embeds on both write and query using FastEmbed with the model named in EMBEDDING_MODEL, defaulting to sentence-transformers/all-MiniLM-L6-v2. Changing the model after you have written data means re-indexing, since old and new vectors are not comparable.

Why only two tools?

Because tool selection degrades as the tool list grows. Two clearly described tools are chosen correctly far more often than a full database API. If you need richer querying, the tool descriptions are configurable and the collection is still a normal Qdrant collection you can hit directly.

How does this compare to the memory MCP server?

The memory server stores explicit entities and relations in a readable graph — precise, auditable, and only recalls what you can name. Qdrant recalls by meaning across unstructured text, which scales better and is fuzzier. Teams often run both.

Can I run it without a Qdrant server?

Yes. Set QDRANT_LOCAL_PATH and it uses an embedded on-disk instance with no service to run. That is fine for one client on one machine; use a real instance once more than one process needs the same collection.

Other MCP servers

More on MCP Playground

Qdrant MCP Server — Vector Search Memory for AI Agents