Verified

Qdrant MCP Server

Qdrant vector search engine integration for semantic memory and data retrieval.

Data last scanned yesterday · Reviewed last month

732 tools1,485PythonApache-2.0

Overview

The Qdrant MCP server functions as a semantic memory layer, allowing LLMs to store and query information within the Qdrant vector database. It provides two primary tools: qdrant-store for saving information and associated metadata, and qdrant-find for retrieving relevant data based on search queries.

Our verdict

With a security score of 58/100, this server is classified as high-risk. This rating stems from the fact that it is a community-maintained project rather than an official Qdrant release, and security-critical features like read-only mode and authentication methods have not yet been reviewed. Given the high-risk classification and lack of verified security audits, this tool is best suited for experimental environments or non-critical personal workflows where sensitive data exposure is not a concern.

  • Zero direct dependencies minimize the software supply-chain surface
  • Active development with commits within the last seven days
  • Standardized Apache-2.0 open-source licensing
  • Community-maintained rather than supported by the official Qdrant vendor
  • Read-only access modes remain unreviewed
  • Authentication and OAuth implementation details have not been audited

Tools

ToolDescriptionRisk
qdrant-storeStore some information in the Qdrant databasemedium
qdrant-findRetrieve relevant information from the Qdrant databaselow

Compatibility

ClientLocalDockerRemoteRead-only
ChatGPT
Claude Desktop
Cursor
VS Code
Windsurf

Frequently asked questions

Can I connect to a local Qdrant database instead of a remote server?

Yes, you can provide a local path using the QDRANT_LOCAL_PATH environment variable. Note that you cannot specify both QDRANT_URL and QDRANT_LOCAL_PATH simultaneously.

How can I prevent the server from writing data to my database?

You can enable read-only mode by setting the QDRANT_READ_ONLY environment variable to true, which disables the qdrant-store tool.

Is it possible to override the default embedding model?

Yes, you can specify a different model using the EMBEDDING_MODEL environment variable, though currently only the fastembed provider is supported.

Does the server require a default collection name?

A default collection name is not strictly required, but if you do not set one, you must provide the collection_name parameter every time you call the qdrant-store or qdrant-find tools.

How many search results does the server return by default?

The server returns a maximum of 10 search results by default, though this limit can be adjusted using the QDRANT_SEARCH_LIMIT environment variable.

Alternatives

Changelog

Badge

Qdrant MCP Server security score, rated on RepoAI

Maintain this server? Add the live badge to your README.