Memgraph AI Toolkit
A unified mono-repo for integrating AI-powered graph tools on top of Memgraph.
This repository contains the following libraries:
-
memgraph-toolbox Core Python utilities and CLI tools for querying and analyzing a Memgraph database. The package is available on the PyPi
-
langchain-memgraph A LangChain integration package, exposing Memgraph operations as LangChain tools and toolkits. The package is available on the PyPi
-
mcp-memgraph An MCP (Model Context Protocol) server implementation, exposing Memgraph tools over a lightweight STDIO protocol. The package is available on the PyPi
-
agents An intelligent database migration agent that automates the process of migrating from MySQL or Postgresql to Memgraph. Features automated schema analysis, intelligent graph modeling with interactive refinement, and data migration with validation.
Usage examples
For individual examples on how to use the toolbox, LangChain, MCP, or agents, refer to our documentation:
- Langchain examples
- MCP examples
- SQL2Graph migration examples - Interactive MySQL to Memgraph migration workflow
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]"
Recommend MCP Servers 💡
cdata-jdbc-mcp-server
A read-only MCP Server that connects Claude Desktop to external data through CData JDBC Drivers
gralio-mcp
SaaS Database MCP by Gralio.ai
database-mcp
A server that helps people access and query data in databases using the Legion Query Runner with Model Context Protocol (MCP) in Python.
@alanse/mcp-neo4j-server
An MCP server that provides integration between Neo4j graph database and Claude Desktop, enabling graph database operations through natural language interactions.
mcp-server-mariadb
An MCP server implementation for retrieving data from MariaDB with read-only access
@rijk/directus-mcp-server
MCP server that allows AI tools to connect to and use Directus API