MCP Qdrant Memory MCP Server

MCP server for enabling the named memory graphs to be persisted to a qdrant instance.

Local serverstdioTypeScript

What is the MCP Qdrant Memory MCP server?

MCP server for enabling the named memory graphs to be persisted to a qdrant instance. That is what the mcp qdrant memory mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

This MCP server provides a knowledge graph implementation with semantic search capabilities powered by Qdrant vector database.

  • Graph-based knowledge representation with entities and relations
  • File-based persistence (memory.json)
  • Semantic search using Qdrant vector database
  • OpenAI embeddings for semantic similarity
  • HTTPS support with reverse proxy compatibility
  • Docker support for easy deployment

The tools it exposes

The server publishes 1 tool. What each one is for:

  • Synchronization — When entities or relations are modified: 1. Changes are written to memory.json 2. Embeddings are generated using OpenAI 3. Vectors are stored in

What it needs from you

Configuration is passed through the environment: OPENAI_API_KEY, QDRANT_API_KEY, QDRANT_URL, QDRANT_COLLECTION_NAME. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

How it compares

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP Qdrant Memory's toolset — Synchronization — is a fair guide to whether it matches your workflow. It is maintained by delorenj; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
SynchronizationWhen entities or relations are modified: 1. Changes are written to memory.json 2. Embeddings are generated using OpenAI 3. Vectors are stored in Qdrant 4. Both storage systems remain consistent

How to install the MCP Qdrant Memory MCP server

### Add to MCP settings:
```json
{
  "mcpServers": {
    "memory": {
      "command": "/bin/zsh",
      "args": ["-c", "cd /path/to/server && node dist/index.js"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key",
        "QDRANT_API_KEY": "your-qdrant-api-key",
        "QDRANT_URL": "http://your-qdrant-server:6333",
        "QDRANT_COLLECTION_NAME": "your-collection-name"
      },
      "alwaysAllow": [
        "create_entities",
        "create_relations",
        "add_observations",
        "delete_entities",
        "delete_observations",
        "delete_relations",
        "read_graph",
        "search_similar"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
QDRANT_API_KEYCredential the server authenticates with.Yes
QDRANT_URLEndpoint or connection string the server talks to.Yes
QDRANT_COLLECTION_NAMEConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP Qdrant Memory to Synchronization.

Frequently asked questions

It connects MCP Qdrant Memory to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Synchronization) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Qdrant Memory directly.