Skip to main content
Glama

qdrant-mcp-server

A generic MCP server for Qdrant — store, search, list, and delete over any collection.

Unlike qdrant/mcp-server-qdrant, this server uses a plain (unnamed) vector, so it works out of the box with collections created the "default" way — e.g. by LangChain's or n8n's Qdrant node — instead of requiring the named-vector convention (fast-{model}) the official server hardcodes.

Features

  • Multi-collection: QDRANT_COLLECTION is only a default. Every tool accepts an optional collection_name, so one running instance can serve multiple collections.

  • Plain vectors: compatible with collections populated by other tools/pipelines, not just this server.

  • OpenAI embeddings, with automatic token-aware truncation of oversized input.

Related MCP server: Qdrant MCP Server

Tools

Tool

Description

qdrant_store

Embed and store a piece of text, with optional metadata and a stable id (upsert).

qdrant_find

Semantic search over stored content.

qdrant_delete

Delete a point by the id given to qdrant_store.

qdrant_list_collections

List all collections available on the Qdrant server.

Configuration

Set these environment variables (see .env.example):

Variable

Required

Description

QDRANT_URL

yes

Qdrant server URL.

QDRANT_API_KEY

no

Qdrant API key, if auth is enabled.

QDRANT_COLLECTION

no

Default collection name. Omit to require collection_name on every call.

OPENAI_API_KEY

yes

Used to generate embeddings.

OPENAI_EMBED_MODEL

no

Default text-embedding-3-small.

OPENAI_EMBED_DIMS

no

Default 1536 (1536 for text-embedding-3-small/ada-002, 3072 for text-embedding-3-large).

Running

Docker

docker build -t qdrant-mcp-server .
docker run --rm -p 8000:8000 --env-file .env qdrant-mcp-server

Locally

pip install -r requirements.txt
export $(cat .env | xargs)  # or set the variables another way
python server.py

The server speaks MCP over SSE on 0.0.0.0:8000.

Using with an MCP client

Point your client at the SSE endpoint, e.g. for a docker-compose service named mcp-qdrant:

{
  "mcpServers": {
    "qdrant": {
      "url": "http://localhost:8000/sse"
    }
  }
}

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    Not graded
    maintenance
    Provides RAG capabilities for semantic document search using Qdrant vector database and Ollama/OpenAI embeddings, allowing users to add, search, list, and delete documentation with metadata support.
    16 npm
    16
    -
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables semantic search and document management using a local Qdrant vector database with OpenAI embeddings. Supports natural language queries, metadata filtering, and collection management for AI-powered document retrieval.
    35 npm
    37
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables storing and retrieving information using semantic search with Qdrant vector database. Acts as a memory layer for LLMs to persistently store and semantically search through information and metadata.
    Apache 2.0