Better Qdrant MCP Server

🚀 Better Qdrant MCP Server

An enhanced Qdrant Vector Database Model Context Protocol (MCP) server. This server provides powerful tools for managing Qdrant collections, adding documents, and performing semantic searches.

✨ Features

• List Collections: View all available Qdrant collections.
• Add Documents: Process and add documents to Qdrant collections, supporting multiple embedding services.
• Search: Perform semantic searches on your vector database.
• Delete Collections: Remove collections from your Qdrant database.

📦 Installation

You can install the server globally using npm:

npm install -g better-qdrant-mcp-server

Or use it directly with npx:

npx better-qdrant-mcp-server

🛠️ Configuration

The server is configured using environment variables. You can create a .env file in the project root directory to set these variables:

# Qdrant Configuration
QDRANT_URL=http://localhost:6333
QDRANT_API_KEY=Your_API_Key (if required)

# Embedding Service API Keys
OPENAI_API_KEY=Your_OpenAI_API_Key
OPENROUTER_API_KEY=Your_OpenRouter_API_Key
OLLAMA_ENDPOINT=http://localhost:11434

💪 Supported Embedding Services

• OpenAI: Requires an API key.
• OpenRouter: Requires an API key.
• Ollama: Local embedding model (default endpoint: http://localhost:11434).
• FastEmbed: Local embedding model.

🤝 Using with Claude

To use this MCP server with Claude, add it to your MCP settings configuration file:

{
  "mcpServers": {
    "better-qdrant": {
      "command": "npx",
      "args": ["better-qdrant-mcp-server"],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "QDRANT_API_KEY": "Your_API_Key (if required)",
        "DEFAULT_EMBEDDING_SERVICE": "ollama",
        "OPENAI_API_KEY": "Your_OpenAI_API_Key",
        "OPENAI_ENDPOINT": "https://api.openai.com/v1",
        "OPENROUTER_API_KEY": "Your_OpenRouter_API_Key",
        "OPENROUTER_ENDPOINT": "https://api.openrouter.com/v1",
        "OLLAMA_ENDPOINT": "http://localhost:11434",
        "OLLAMA_MODEL": "nomic-embed-text"
      }
    }
  }
}

💻 Usage Examples

Basic Usage

List Collections

use_mcp_tool
server_name: better-qdrant
tool_name: list_collections
arguments: {}

Add Documents

use_mcp_tool
server_name: better-qdrant
tool_name: add_documents
arguments: {
  "filePath": "/path/to/your/document.pdf",
  "collection": "my-collection",
  "embeddingService": "openai",
  "chunkSize": 1000,
  "chunkOverlap": 200
}

Search

use_mcp_tool
server_name: better-qdrant
tool_name: search
arguments: {
  "query": "Your_search_query",
  "collection": "my-collection",
  "embeddingService": "openai",
  "limit": 5
}

Delete Collection

use_mcp_tool
server_name: better-qdrant
tool_name: delete_collection
arguments: {
  "collection": "my-collection"
}

📋 Prerequisites

• Node.js >= 18.0.0
• A running Qdrant server (local or remote)
• API keys for the embedding services you use

📄 License

MIT