Mcp Qdrant Docker

Name: Mcp Qdrant Docker
Author: RollandMELET

@RollandMELET

リポジトリ

Mcp Qdrant Docker について

Docker configuration for Qdrant MCP server

基本情報

カテゴリ

データベース

ランタイム

shell

トランスポート

stdio

公開者

RollandMELET

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "qdrant": {
      "url": "http://votre-adresse-ip:8000/sse",
      "transport": "sse"
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Mcp Qdrant Docker?

Mcp Qdrant Docker is a server that implements the Model Context Protocol (MCP) to allow Claude to access a Qdrant vector database deployed on a VPS. It is packaged and deployed via Docker, typically hosted on Coolify.

How to use Mcp Qdrant Docker?

Set the required environment variables (QDRANT_URL, QDRANT_API_KEY, COLLECTION_NAME, EMBEDDING_MODEL) and deploy the Docker container (exposing port 8000 with SSE support). Then configure Claude Desktop by editing claude_desktop_config.json with the server’s URL (including /sse) and "transport": "sse".

Key features of Mcp Qdrant Docker

Docker‑based deployment for Qdrant MCP server
SSE transport for remote connections (port 8000)
Configurable collection, embedding model, and API key
Pre‑defined test collection (ClaudeCollection)

Use cases of Mcp Qdrant Docker

Let Claude perform vector similarity searches on a Qdrant database
Integrate semantic memory or RAG into Claude conversations
Enable remote Claude instances to query a VPS‑hosted vector store

FAQ from Mcp Qdrant Docker

What environment variables are required?

QDRANT_URL, QDRANT_API_KEY, and COLLECTION_NAME must be set. EMBEDDING_MODEL is optional and defaults to sentence-transformers/all-MiniLM-L6-v2.

How do I connect Claude Desktop to this server?

Edit claude_desktop_config.json and add an entry with the server’s public URL (e.g. http://your‑ip:8000/sse) and "transport": "sse".

What default collection and embedding model does it use?

The server uses the collection named ClaudeCollection (set in the README) and the default embedding model is sentence-transformers/all-MiniLM-L6-v2.