Project-scoped Qdrant MCP server for workspace collections with scratchbook functionality. Python port of claude-qdrant-mcp with FastEmbed and project-aware collection management.
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Claude Desktop
Claude Code
Cursor
Add to claude_desktop_config.json:
{
"mcpServers": {
"workspace-qdrant-mcp": {
"command": "cargo",
"args": [
"run",
"--",
"workspace-qdrant-mcp"
]
}
}
}
📋 Copy
Run in terminal:
claude mcp add workspace-qdrant-mcp cargo run -- workspace-qdrant-mcp
📋 Copy
Add to .cursor/mcp.json:
{
"mcpServers": {
"workspace-qdrant-mcp": {
"command": "cargo",
"args": [
"run",
"--",
"workspace-qdrant-mcp"
]
}
}
}
📋 Copy
README Excerpt
Project-scoped vector database for AI assistants, providing hybrid semantic + keyword search with automatic project detection. - **Hybrid Search** - Combines semantic similarity with keyword matching using Reciprocal Rank Fusion - **Project Detection** - Automatic Git repository awareness and project-scoped collections
Tools (13)
CLAUDE_CONFIG_DIR FASTEMBED_MODEL QDRANT_API_KEY QDRANT_URL grep libraries list projects retrieve rules scratchpad search store
Topics
ai-tools asyncio claude-code claude-desktop cli document-management embeddings fastmcp hybrid-search mcp mcp-server model-context-protocol pydantic qdrant search