qdrant-mcp-server

Overview

The Qdrant MCP Server provides comprehensive semantic search capabilities with local-first architecture. It supports multiple embedding providers including Ollama, OpenAI, Cohere, and Voyage AI. The server features advanced code vectorization with AST-aware chunking, Git history indexing, and hybrid search combining semantic and keyword search. It can be deployed locally via stdio transport or remotely as an HTTP server with authentication support.

Try asking AI

After installing, here are 6 things you can ask your AI assistant:

• create_collection

  Create collection with specified distance metric (Cosine/Euclid/Dot)

  Try:Create a collection called 'research_papers' with cosine distanceTry:Create a new document collection named 'notes'
• add_documents

  Add documents with automatic embedding (supports string/number IDs, metadata)

  Try:Add a document about machine learning to my collectionTry:Insert multiple research papers with metadata tags
• semantic_search

  Natural language search with optional metadata filtering

  Try:Search for documents about quantum computingTry:Find all articles mentioning 'blockchain' from 2023
• hybrid_search

  Hybrid search combining semantic and keyword (BM25) search with RRF

  Try:Find documents about 'neural networks' using both semantic and keyword searchTry:Search for 'API documentation' with hybrid approach
• index_codebase

  Index a codebase for semantic code search with AST-aware chunking

  Try:Index my TypeScript project for code searchTry:Index the backend codebase with AST-aware chunking
• search_code

  Search indexed codebase using natural language queries

  Try:Search for authentication middleware in the codebaseTry:Find database connection patterns in the project
• index_git_history

  Index git commit history for semantic search over past changes and fixes

  Try:Index git history of this repository for semantic searchTry:Index the commit history to search for bug fixes
• search_git_history

  Search indexed git history using natural language queries

  Try:Search git history for authentication implementationTry:Find commits related to database schema changes
• contextual_search

  Combined code + git history search with file-commit correlations

  Try:Search for authentication implementation across code and git historyTry:Find how user management evolved over time in code and commits
• federated_search

  Search across multiple repositories with Reciprocal Rank Fusion (RRF) ranking

  Try:Search for payment processing patterns across all repositoriesTry:Find API implementations across multiple codebases
• reindex_changes

  Incrementally re-index only changed files (detects added/modified/deleted)

  Try:Update the index with recent code changesTry:Re-index only the modified files in the project
• delete_documents

  Delete specific documents by ID

  Try:Remove document with ID 'doc123' from the collectionTry:Delete outdated research papers from the database

Comparable tools

Installation

# Clone and install
git clone https://github.com/mhalder/qdrant-mcp-server.git
cd qdrant-mcp-server
npm install

# Start services
podman compose up -d   # Using Podman
docker compose up -d   # Using Docker

# Pull the embedding model
podman exec ollama ollama pull nomic-embed-text

# Build
npm run build

{
  "mcpServers": {
    "qdrant": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/qdrant-mcp-server/build/index.js"]
    }
  }
}

FAQ

Which embedding providers are supported?

The server supports Ollama (default), OpenAI, Cohere, and Voyage AI as embedding providers.

Can I use Qdrant Cloud?

Yes, you can connect to Qdrant Cloud or secured instances using API key authentication.

Compare qdrant-mcp-server with