What is Memgraph MCP Server?

Memgraph MCP Server is a lightweight server implementation of the Model Context Protocol (MCP) designed to connect Memgraph, an in-memory graph database, with Large Language Models (LLMs).

What is the Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how applications provide context to LLMs. It allows LLMs to access and interact with external data sources and tools in a standardized way.

How do I install and run Memgraph MCP Server?

1. Install uv and create a virtual environment.
2. Install dependencies: uv add "mcp[cli]" httpx
3. Run Memgraph MCP server: uv run server.py

How do I connect Memgraph MCP Server to Claude?

1. Install Claude for Desktop.
2. Add the Memgraph server to Claude config (claude_desktop_config.json) with the command and arguments to run the server.

What is the run_query() tool?

run_query() is a tool that allows you to run a Cypher query against Memgraph directly from the LLM.

What is the get_schema() resource?

get_schema() is a resource that retrieves Memgraph schema information, allowing the LLM to understand the structure of your graph database.

Why do I need --schema-info-enabled=True?

The --schema-info-enabled=True configuration setting allows the LLM to run the SHOW SCHEMA INFO query, which is necessary for the get_schema() resource to function.

Where can I find dummy data to load into Memgraph?

You can load dummy data from Memgraph Lab Datasets.

What is the UBOS platform, and how does Memgraph MCP Server relate to it?

UBOS is a full-stack AI Agent Development Platform. Memgraph MCP Server integrates with UBOS, allowing AI Agents to access and leverage graph data stored in Memgraph.

What are the future plans for Memgraph MCP Server?

Future plans include releasing a TypeScript version of the server and migrating the project into the Memgraph AI Toolkit repository.