Qdrant MCP Server
Empower your AI to interact directly with your Qdrant vector database — query clusters, perform similarity searches, and manage collections effortlessly.
Vinkius AI Gateway supports streamable HTTP and SSE.
Works with every AI agent you already use
…and any MCP-compatible client
Qdrant MCP Server: see your AI Agent in action
Built-in capabilities (7)
count
Counts the total number of points in a collection
delete
This action is irreversible. Deletes specific points from a collection
get_collection
Retrieves detailed information about a specific collection
get_points
Retrieves specific points by their IDs
list_collections
Lists all collections in the Qdrant instance
scroll
Returns points with their payloads. Scrolls through points in a collection, useful for pagination
search
You must provide a JSON array of floats for the query vector. Performs a nearest neighbor vector search in a collection
What this connector unlocks
Connect your Qdrant vector database (Cloud or Self-Hosted) to any AI agent and bring powerful semantic retrieval and database management into your conversation.
What you can do
- Discover Collections — List all vector collections in your cluster, fetch detailed distance metrics, and monitor total payload points instantly
- Semantic Vector Search — Perform nearest neighbor similarity searches. Pass a JSON array of floats and retrieve the exact payloads matching your query
- Data Management — Read specific points by ID or scroll sequentially through giant datasets to debug payloads and embedding quality
- Mutation Operations — Delete redundant data points safely without building separate admin scripts
How it works
1. Subscribe to this server
2. Provide your Qdrant Base URL and API Key
3. Start querying your embeddings directly from Claude, Cursor, or any MCP-compatible client
Who is this for?
- AI & ML Engineers — query embedded spaces directly from your console while building RAG (Retrieval-Augmented Generation) applications
- Data Scientists — inspect payloads and test distance parameters on live indices without launching Jupyter Notebooks
- Backend Developers — manage vector cluster configuration and clear bad datasets efficiently
Frequently asked questions
Give your AI agents the power of Qdrant
Access Qdrant and 2,000+ MCP servers — ready for your agents to use, right now. No glue code. No custom integrations. Just plug Vinkius AI Gateway and let your agents work.
More in this category
Cognee
4 toolsBuild knowledge graphs from unstructured data — ingest text, extract entities and relationships, and search with graph-aware AI reasoning.
Groq
8 toolsEmpower LLM applications via Groq — perform ultra-fast LPU-accelerated chat completions, handle audio transcription and translation, and use JSON mode directly from any AI agent.
Exa
3 toolsSemantic search engine built for AI — find conceptually relevant web content, not just keyword matches. Powered by neural search technology.
You might also like
HubSpot Sales Hub
9 toolsManage deals, pipelines, products, quotes, and meetings in your HubSpot Sales Hub through natural conversation.
CleverTap
8 toolsManage customer engagement and analytics via CleverTap — track campaigns, monitor user segments, and audit event data directly from any AI agent.
Internet Archive Search
12 toolsSearch 40M+ books, videos, audio, software across the Internet Archive.