$ loading_
Use Qdrant via MCP for vector search, collection management, and semantic retrieval.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-server-qdrant" yet — see the docs or source repo.
Use the Qdrant MCP server to search the collection named knowledge-base for the 5 items most similar to “best practices for enterprise knowledge base access control,” and return the title, similarity score, and summary.
A ranked list of 5 relevant documents with similarity scores and key summaries.
Through the Qdrant MCP server, list all available collections and highlight the vector size, point count, and configuration summary for the customer-support collection.
A collection inventory plus a structural and capacity overview of the specified collection.
Use the Qdrant MCP server to help design retrieval for a RAG application: first explain how to organize a product-docs collection, then provide a query example for “refund policy changes,” and explain how the returned results should be used for answer generation.
Guidance on RAG-oriented collection design, a retrieval example, and how to use results in generation.
Query and manage LlamaIndex documents stored in Qdrant vector databases.
Run Qdrant for vector storage and semantic search with MCP integration.
Give AI coding agents persistent semantic memory and workspace-aware code search.
Index PDFs into Qdrant and enable semantic search and RAG document QA.
Securely read files, browse directories, and run filtered RAG knowledge searches.
Orchestrate vector search, graph queries, and web crawling for agentic RAG workflows.