Qdrant MCP Server

MCPOpen SourceApache-2.083.5

by qdrant • Search & Retrieval

An MCP server that provides semantic memory storage and retrieval on top of the Qdrant vector search engine.

Example Use Cases

1
Persistent semantic memory storage and retrieval backed by a vector database for long-term context.
2
Perform semantic code search by storing code snippets (in metadata) and retrieving relevant examples via natural language queries.
3
Integrate a Qdrant-backed context layer into tools like Claude Desktop, Cursor, or VS Code via SSE or streamable HTTP transports.

Description

This repository implements a Model Context Protocol (MCP) server that stores and retrieves semantic memories using Qdrant. It exposes two main tools (qdrant-store and qdrant-find) for storing information with metadata and performing semantic search, and uses FastEmbed-compatible embeddings by default. The server supports multiple transports (stdio, SSE, streamable-http), Docker deployment, and integrations with clients like Cursor, Claude, and VS Code. It is designed to act as a semantic memory layer for LLM agents and developer tooling.

Capabilities(2 total)

Tools (2)

qdrant-find

Look up memories in Qdrant. Use this tool when you need to: - Find memories by their content - Access memories for further analysis - Get some personal information about the user

query:string*collection_name:string*

qdrant-store

Keep the memory for later use, when you are asked to remember something.

information:string*collection_name:string*metadata:any

Quick Actions

View on GitHub

Security

Scanned 3 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

B65/100

11/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities2 Tools / 0 Prompts / 0 Resources

Ownerqdrant

CategorySearch & Retrieval

DependenciesStandalone

Set Your Username