Qdrant MCP server
The Qdrant MCP server gives AI agents semantic memory in a Qdrant collection, with tools to store information and retrieve relevant entries through natural-language queries.
Checked by CookiesForAI on : repository facts (stars, last push, archived) re-read from GitHub.
Written by
Connect Qdrant
Claude Code with a local Qdrant server
claude mcp add qdrant \
-e QDRANT_URL="http://localhost:6333" \
-e COLLECTION_NAME="my-collection" \
-- uvx mcp-server-qdrantCodex with a local Qdrant server
codex mcp add qdrant \
--env QDRANT_URL="http://localhost:6333" \
--env COLLECTION_NAME="my-collection" \
-- uvx mcp-server-qdrantClaude Desktop with Qdrant Cloud
{
"qdrant": {
"command": "uvx",
"args": ["mcp-server-qdrant"],
"env": {
"QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
"QDRANT_API_KEY": "your_api_key",
"COLLECTION_NAME": "your-collection-name",
"EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
}
}
}Set QDRANT_URL and COLLECTION_NAME for a server deployment. Add QDRANT_API_KEY for Qdrant Cloud, or replace QDRANT_URL and QDRANT_API_KEY with QDRANT_LOCAL_PATH for a local database file.
Or paste this into your coding agent: Connect the Qdrant MCP server to my coding agent using its documented setup: https://github.com/qdrant/mcp-server-qdrant. Checked by CookiesForAI on : repository facts (stars, last push, archived) re-read from GitHub.
What the Qdrant MCP server does
The Qdrant MCP server is an official open-source semantic memory layer for a Qdrant collection. It exposes qdrant-store to save information with optional JSON metadata and qdrant-find to retrieve relevant entries from a natural-language query, returning each match as a separate message.
The Qdrant MCP server runs on your machine or infrastructure and can target Qdrant Cloud, a local Qdrant server or a local database file. It creates the collection when needed and generates embeddings with FastEmbed, so a separate embedding provider key is not required.
The Qdrant MCP server uses stdio by default and also supports SSE and streamable HTTP for remote connections. When exposed remotely, it has no built-in authentication, so Qdrant says to protect it with third-party security such as an authenticated reverse proxy or private network.
Tools it gives your agent
qdrant-storeqdrant-find
We also list this company's other pages: Qdrant product page.
When to use Qdrant
- You want an assistant to remember notes or facts and retrieve them later by semantic similarity.
- You want a code snippet library that stores natural-language descriptions with code in metadata and searches them by meaning.
- You need the same memory tools against Qdrant Cloud, a local server or a local database file.
- You want search-only access to a collection by disabling qdrant-store with QDRANT_READ_ONLY=true.
When to pick something else
- Choose Qdrant Cloud MCP instead when the job is to manage clusters, serverless spaces, backups, access or billing; the open-source server works on collection data.
- Do not expose its SSE or streamable HTTP endpoint without another authentication layer or a private network, because the server has no built-in authentication.
What Qdrant needs
- uvx
- A Qdrant server URL and API key, or a local Qdrant database path
What the Qdrant MCP server costs
Free and open source under Apache-2.0; Qdrant Cloud is optional and has free and paid tiers.
Current prices: qdrant.tech . We do not list prices because vendors change them often. Check the publisher's own page.
Other MCP servers for databases
- DBHub: DBHub is an open-source MCP server by Bytebase that gives AI agents SQL access to PostgreSQL, MySQL, MariaDB, SQL Server, Oracle and SQLite through one server with two default tools.
- MongoDB: The MongoDB MCP server gives AI agents access to MongoDB databases and MongoDB Atlas: run find and aggregate queries, inspect schemas and indexes, and create or manage Atlas clusters and users.
- Neon: The Neon MCP server gives AI agents control of Neon serverless Postgres: create projects and branches, run SQL, inspect schemas, find slow queries and run migrations on a branch before applying them.
- Postgres MCP Pro: Postgres MCP Pro is an open-source MCP server that gives AI agents access to a PostgreSQL database, with schema browsing, safe SQL execution, EXPLAIN plans, index recommendations and database health checks.