io.github.avaazquezz/mcp-qdrant
Related Servers
Alternatives to io.github.avaazquezz/mcp-qdrant
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to interact with a Qdrant vector database, including embedding generation and vector search operations.MIT
- AlicenseAqualityCmaintenanceExposes hybrid retrieval (dense embeddings + BM25 + RRF) and document operations (search, fetch, rerank) as MCP tools, using Qdrant and OpenAI embeddings for local or server mode.3MIT
- FlicenseNot gradedqualityDmaintenanceEnables interaction with Qdrant vector database for storing, searching, and managing vectors with automatic text embedding.1-
- FlicenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to perform semantic search, manage vectors, and interact with Pinecone vector databases through standardized MCP tools. Supports querying, upserting, deleting vectors and monitoring database statistics for knowledge base operations.4 npm-
- FlicenseNot gradedqualityCmaintenanceEnables RAG (Retrieval-Augmented Generation) with tools for vector search, document access, and OpenAI integration, plus MySQL storage and file system operations via MCP.-
- AlicenseNot gradedqualityBmaintenanceEnables agents to turn documents into vectors, perform approximate nearest neighbor search with HNSW, and filter by metadata via MCP tools for RAG workflows.MIT
TDQS
Scored across 13 tools
Each tool targets a distinct operation on either collections, points, or the server itself. Collection existence vs. info are adjacent but clearly separated by their boolean-vs-detailed-output behavior.
Tools mostly follow a consistent qdrant_<resource>_<action> snake_case pattern. qdrant_query and qdrant_health_check deviate slightly by omitting the resource segment, but the overall pattern remains predictable.
13 tools is well-scoped for a Qdrant MCP server: collection lifecycle, point operations, search, and health check all have a place. No tool feels redundant or out of scope.
The core surface is solid: collections can be created, listed, inspected, updated, and deleted, and points can be upserted, fetched, deleted, scrolled, counted, and queried. The main gap is that collection_update references a qdrant_collection_vector_create tool that is not actually exposed, making it impossible to add a new named vector to an existing collection.