Memgraph AI Toolkit

What is Memgraph AI Toolkit about?

Memgraph AI Toolkit provides a set of libraries that enable developers to create, query, and manage AI‑driven graph applications on the Memgraph graph database. It bundles core Python utilities, a LangChain integration, an MCP server for lightweight communication, and an experimental agent that automates MySQL‑to‑Memgraph migrations using LLMs.

How to use Memgraph AI Toolkit?

1. Start a Memgraph instance (e.g., with Docker) that has schema‑info enabled.
2. Install any package in editable mode using uv pip install -e <package-path>[test].
3. Run the test suite to verify the installation (pytest -s <package>/tests).
4. Invoke the desired component:
   • Use memgraph-toolbox for direct Python queries and CLI utilities.
   • Import langchain_memgraph to expose Memgraph operations as LangChain tools.
   • Run the MCP server by installing mcp-memgraph and integrating it with your application.
   • Execute the migration agent with uv run main.py inside integrations/agents after configuring .env with MySQL and Memgraph credentials.

Key Features of Memgraph AI Toolkit

• Core Python utilities and CLI for graph queries and analysis.
• LangChain integration exposing Memgraph as tools and toolkits.
• MCP server implementation for lightweight STDIO‑based communication.
• Experimental migration agent that:
  • Analyses MySQL schemas automatically.
  • Generates graph models powered by LLMs.
  • Supports interactive refinement via natural‑language feedback.
  • Performs end‑to‑end data migration with validation and rollback.
• Real‑time progress monitoring and detailed logging.
• Fully testable packages with pytest and environment‑based configurations.

Use Cases of Memgraph AI Toolkit

• Building AI‑enhanced recommendation systems that leverage graph relationships stored in Memgraph.
• Creating knowledge graphs where LangChain agents can retrieve and reason over graph data.
• Integrating LLMs with graph databases for dynamic query generation and tool usage.
• Automated migration from relational databases (MySQL) to Memgraph for graph‑centric analytics.
• Rapid prototyping of graph‑based AI services using the provided CLI and Python utilities.

FAQ from the Memgraph AI Toolkit

Q: Do I need a Memgraph license to use the toolkit? A: The toolkit works with any Memgraph instance, including the community edition.

Q: Which Python package manager is recommended? A: The README uses uv, but pip works as well.

Q: How do I provide my OpenAI API key for LangChain tests? A: Create a .env file with OPENAI_API_KEY=<your‑key> in the integrations/langchain-memgraph directory.

Q: Is the migration agent production‑ready? A: It is marked as experimental; it is suitable for testing and proof‑of‑concept migrations.

Q: Can I run the MCP server as a separate service? A: Yes, after installing mcp-memgraph, you can import and start the server from your application code.

Memgraph AI Toolkit

A unified mono-repo for integrating AI-powered graph tools on top of Memgraph.
This repository contains the following libraries:

1. memgraph-toolbox Core Python utilities and CLI tools for querying and analyzing a Memgraph database. The package is available on the PyPi

2. langchain-memgraph A LangChain integration package, exposing Memgraph operations as LangChain tools and toolkits. The package is available on the PyPi

3. mcp-memgraph An MCP (Model Context Protocol) server implementation, exposing Memgraph tools over a lightweight STDIO protocol. The package is available on the PyPi

4. agents ⚡ Experimental An intelligent database migration agent that automates the process of migrating from MySQL to Memgraph using LLM-powered graph modeling and analysis. Features automated schema analysis, intelligent graph modeling with interactive refinement, and data migration with validation.

Key Features

Migration Agent Capabilities

• 🔍 Intelligent Schema Analysis: Automatically analyzes MySQL database structure and relationships
• 🧠 LLM-Powered Graph Modeling: Uses AI to create optimal graph models from relational schemas
• 🔄 Interactive Refinement: Allows users to refine graph models through natural language feedback
• ⚡ Automated Migration: Handles complete data migration with validation and rollback capabilities
• 📊 Progress Monitoring: Real-time migration progress tracking with detailed logging
• 🛡️ Data Validation: Comprehensive pre and post-migration data integrity checks

Usage examples

For individual examples on how to use the toolbox, LangChain, MCP, or agents, refer to our documentation:

• Langchain examples
• MCP examples
• Agent migration examples - Interactive MySQL to Memgraph migration workflows

Developing locally

You can build and test each package directly from your repo. First, start a Memgraph MAGE instance with schema info enabled:

docker run -p 7687:7687 \
  --name memgraph \
  memgraph/memgraph-mage:latest \
  --schema-info-enabled=true

Once Memgraph is running, install any package in “editable” mode and run its test suite. For example, to test the core toolbox:

uv pip install -e memgraph-toolbox[test]
pytest -s memgraph-toolbox/src/memgraph_toolbox/tests

Core tests

To test the core toolbox, just run:

uv pip install -e memgraph-toolbox[test]
pytest -s memgraph-toolbox/src/memgraph_toolbox/tests

Langchain integration tests

To run the LangChain tests, create a .env file with your OPENAI_API_KEY, as the tests depend on LLM calls:

uv pip install -e integrations/langchain-memgraph[test]
pytest -s integrations/langchain-memgraph/tests

MCP integration tests

uv pip install -e integrations/mcp-memgraph[test]
pytest -s integrations/mcp-memgraph/tests

Agent integration tests

uv pip install -e integrations/agents[test]
pytest -s integrations/agents/tests

To run a complete migration workflow with the agent:

cd integrations/agents
uv run main.py

Note: The agent requires both MySQL and Memgraph connections. Set up your environment variables in .env based on .env.example.

If you are running any test on MacOS in zsh, add "" to the command:

uv pip install -e memgraph-toolbox"[test]"