Qdrant MCP Server
About
A dual-protocol server that provides both FastAPI and FastMCP clients for accessing Qdrant knowledge graph operations. It is designed for developers who need to interact with Qdrant vector databases using either REST APIs or the Model Context Protocol.
Details
- Author
- davidwynter
- Downloads
- 340
- Categories
- Database
Jump to
- Flexible server selection via CLI argument
- Shared configuration and Qdrant client
- Consistent endpoints across both protocols
- Poetry for dependency management
- Environment variable configuration
- Production-ready build and deployment instructions
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Qdrant MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install dependencies with Poetry after cloning the repository. Configure environment variables (QDRANT_URL, OPENAI_API_KEY, etc.). Run the server using python -m qdrant_mcpserver.main with an optional --server-type argument to choose between FastAPI (default: FastMCP). Both servers expose the same endpoints.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"qdrant mcp server": {
"qdrant_mcpserver": {
"command": "python",
"args": [
"-m",
"qdrant_mcpserver.main",
"--server-type",
"fastmcp"
]
}
}
}
}McpServers
{
"qdrant_mcpserver": {
"command": "python",
"args": [
"-m",
"qdrant_mcpserver.main",
"--server-type",
"fastmcp"
]
}
}Qdrant MCP Server
A dual-protocol server for Qdrant knowledge graph operations, supporting both FastAPI and FastMCP protocols.
Project Structure
src/qdrant_mcpserver/
├── __init__.py
├── config.py # Configuration settings
├── qdrant_client.py # Qdrant operations
├── fastapi_server.py # FastAPI implementation
├── fastmcp_server.py # FastMCP implementation
└── main.py # CLI entry point
File Descriptions
config.py
- Loads environment variables
- Contains settings for:
- Qdrant connection (URL, API key)
- OpenAI API key
- Collection names
- Server ports
- Uses pydantic for validation
qdrant_client.py
- Implements core Qdrant operations:
- Collection management
- Node upsert/delete
- Vector search
- Handles embedding generation via OpenAI
- Provides service layer for both server types
fastapi_server.py
- FastAPI implementation with:
- RESTful endpoints
- CORS middleware
- OpenAPI documentation
- Endpoints:
- POST /nodes/upsert
- POST /nodes/search
- DELETE /nodes
- GET /health
fastmcp_server.py
- FastMCP implementation with:
- MCP protocol compliance
- Authentication support
- Standardized response formats
- Same endpoints as FastAPI but with MCP envelope
main.py
- CLI entry point with:
- Server type selection (--server-type)
- Unified logging
- Port configuration
- Runs either FastAPI or FastMCP server
Installation
1. Install Poetry (if not installed):
curl -sSL https://install.python-poetry.org | python3 -
2. Clone repository:
git clone https://github.com/your-repo/qdrant-mcpserver.git
cd qdrant-mcpserver
3. Install dependencies:
poetry install
4. Configure environment:
```bash
cp .env.example .env
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
