agents-libagents-lib
AgentsMCP ServersWorkflowsTutorialsComparisonsTemplatesNewsAbout
🔌

Qdrant MCP

Database•⭐ 950

Search and manage Qdrant vector database for RAG, semantic search, and AI applications.

GitHubWebsite →
Claude DesktopCursorWindsurf

Overview

Search and manage Qdrant vector database for RAG, semantic search, and AI applications.

Setup

Run with npx:

npx -y @modelcontextprotocol/server-qdrant

Configuration

QDRANT_URL, QDRANT_API_KEY environment variables

Documentation

Qdrant MCP (Enhanced)

Overview

Qdrant MCP provides access to Qdrant vector database for RAG and semantic search.

Features

  • Vector search
  • Collection management
  • Payload filtering
  • Hybrid search
  • Sparse vectors

Installation

npx -y @modelcontextprotocol/server-qdrant

Configuration

Set up Qdrant credentials:

export QDRANT_URL=http://localhost:6333
export QDRANT_API_KEY=your_api_key

Available Operations

OperationDescription
SearchVector similarity search
UpsertAdd vectors
DeleteRemove vectors
List CollectionsGet all collections
Create CollectionNew collection

Usage Examples

Search

{
  "action": "search",
  "collection_name": "documents",
  "vector": [0.1, 0.2, 0.3, ...],
  "limit": 10,
  "with_payload": true
}

Upsert

{
  "action": "upsert",
  "collection_name": "documents",
  "points": [
    {
      "id": "doc1",
      "vector": [0.1, 0.2, 0.3, ...],
      "payload": { "title": "Introduction to AI", "category": "tech" }
    }
  ]
}

Create Collection

{
  "action": "create_collection",
  "collection_name": "my_vectors",
  "vector_size": 1536,
  "distance": "Cosine"
}

Pros

  • ✅ High-performance vector search
  • ✅ Rich filtering capabilities
  • ✅ Production-ready
  • ✅ Multiple distance metrics

Cons

  • ❌ Requires Qdrant instance
  • ❌ Vector dimension management
  • ❌ Additional infrastructure

Resources