Free🇺🇸
Open-source MCP server from Google that connects AI agents to Google Cloud databases and many other databases.
Qdrant MCP Server overview and key facts (October 2026)
Qdrant's official MCP server that gives AI assistants a semantic memory based on the Qdrant vector database.
Free
What is Qdrant MCP Server?
The Qdrant MCP Server is Qdrant's official Model Context Protocol server that adds a semantic memory layer to AI assistants, storing information in the Qdrant vector database and retrieving it by meaning.
The server provides two tools: qdrant-store saves information with optional metadata, and qdrant-find retrieves relevant entries by semantic similarity. Embeddings are computed with FastEmbed, by default the model sentence-transformers/all-MiniLM-L6-v2. It connects to a remote Qdrant instance via QDRANT_URL or to a local path, and supports stdio, Server-Sent Events and streamable HTTP. Qdrant's GitHub organization lists Germany as its location. The GitHub API showed about 1,500 stars and a push on September 4, 2026.
Qdrant MCP Server AI features and use cases
- Gives assistants long-term memoryAssistants store facts, decisions or snippets and find them again in later sessions by meaning. Teams avoid repeating the same context in every conversation.
- Searches code semanticallyBy adjusting tool descriptions, the server works as a semantic code search across projects. Developers find similar implementations even when names differ.
- Keeps memory in your own databaseThe memory lives in a Qdrant instance you control, locally or in the cloud. Knowledge collected by assistants stays in company infrastructure.
What sets Qdrant MCP Server apart
- Maintained by Qdrant, a vector database vendor based in Germany.
- Computes embeddings locally with FastEmbed, so no separate embedding API is needed.
Where Qdrant MCP Server is strongest
Germany Available internationally
Qdrant lists Germany as its location; the server runs locally or with a Qdrant instance in any region.
Questions to ask before you buy Qdrant MCP Server
Decide what assistants may store, since memory can accumulate personal or confidential information over time; plan retention and deletion. Choose where the Qdrant instance runs: local, self-hosted or Qdrant Cloud. The default embedding model is English-focused, so test retrieval quality for German content.
Using Qdrant MCP Server in the EU: GDPR and AI Act
- Data locationNot published by the vendor.
- Data processing agreementNot published by the vendor: ask for one (Art. 28 GDPR).
- EU AI ActCheck whether the AI prepares decisions about people. If not, the high-risk rules usually do not apply. The high-risk obligations apply from December 2, 2027 (Digital Omnibus).
General information with sources, not legal advice.
Qdrant MCP Server reviews
No reviews yet. Be the first to share how your team uses it.
Every review shows its verification level. We read each one before it goes live. How we check reviews
Questions about Qdrant MCP Server
Do I need Qdrant Cloud?
No. The server can use a local path or any Qdrant instance reachable by URL.
Which embedding model does it use?
FastEmbed with sentence-transformers/all-MiniLM-L6-v2 by default; the model can be configured.
Which transports are supported?
stdio, Server-Sent Events and streamable HTTP, according to the README.
Qdrant MCP Server update historyno updates yet
No changes recorded for Qdrant MCP Server yet.
Changes the vendor made and confirmed user reports, each checked against the vendor's own pages. We review every tool monthly.
Alternatives to Qdrant MCP Server
Tools in the same category (Databases & data sources) with the most overlapping markets.
Free🇺🇸
Official MCP server for MongoDB databases and Atlas clusters with query, schema and administration tools.
Free🇺🇸
Supabase's official MCP server that lets AI assistants query tables, apply migrations, deploy Edge Functions and read logs.