Dragon-Brain MCP Server

How to use Dragon-Brain MCP Server

docker compose up -d

{
  "mcpServers": {
    "dragon-brain": {
      "command": "python",
      "args": ["-m", "claude_memory.server"],
      "env": {
        "FALKORDB_HOST": "localhost",
        "FALKORDB_PORT": "6379",
        "QDRANT_HOST": "localhost",
        "QDRANT_PORT": "6333",
        "EMBEDDING_API_URL": "http://localhost:8001"
      }
    }
  }
}

What is Dragon-Brain MCP Server?

Dragon-Brain is a Python MCP server for Claude Desktop, Cursor, Windsurf with uvx/pip, docker. Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude,. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Key capabilities

• Tool access support
• Shell commands support
• Document generation support
• Anthropic provider support
• Google provider support
• pyproject.toml config support
• Dockerfile config support

Technical details

Install or run Dragon-Brain using uvx/pip. Check iikarus/Dragon-Brain for the latest setup command.

• Built for Python
• Built for Docker
• Built for Rust
• Install or run with uvx/pip
• Install or run with docker
• Works with Claude Desktop
• Works with Cursor
• Works with Windsurf

Requirements and access

Security and permissions

Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.

When to use Dragon-Brain MCP Server

• Use it for connecting agents to external tools and data.
• Use it for integrations workflows.
• Use it for coding workflows.
• Use it for data workflows.
• Use it for claude desktop users.

Built with

Explore related resources

Frequently asked questions