Memgraph MCP server for AI agents

The Memgraph MCP Server implements the Model Context Protocol (MCP) to connect Memgraph graph database with Large Language Models. This lightweight server enables LLMs to query Memgraph and leverage its graph capabilities, allowing for more powerful AI applications with database integration.

Getting Started

Prerequisites

Before setting up the Memgraph MCP Server, you need:

Python environment
Memgraph database
Claude for Desktop (or another MCP-compatible client)

Installation

Install the uv package manager and create a virtual environment:

# Install uv (follow instructions at https://docs.astral.sh/uv/getting-started/installation/)

# Create and activate virtual environment
uv venv

# On Windows
.venv\Scripts\activate

# On macOS/Linux
source .venv/bin/activate

Install required dependencies:
```
uv add "mcp[cli]" httpx
```
Run the Memgraph MCP server:
```
uv run server.py
```

Configuring Claude for Desktop

Download and install Claude for Desktop

Add the Memgraph server to Claude's configuration:

On macOS/Linux:

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows:

code $env:AppData\Claude\claude_desktop_config.json

Add the following configuration (adjust paths to match your system):

{
    "mcpServers": {
      "mpc-memgraph": {
        "command": "/full/path/to/uv",
        "args": [
            "--directory",
            "/full/path/to/mcp-memgraph",
            "run",
            "server.py"
        ]
     }
   }
}

Note: Replace /full/path/to/uv with the actual path to your uv executable. You can find this by running which uv on macOS/Linux or where uv on Windows.

Using Memgraph MCP

Starting the Database

Run Memgraph with MAGE extensions and schema information enabled:

docker run -p 7687:7687 memgraph/memgraph-mage --schema-info-enabled=True

The --schema-info-enabled=True flag is required to allow the LLM to run the SHOW SCHEMA INFO query.

Interacting with Memgraph via Claude

Open Claude Desktop
You should see Memgraph tools and resources listed in the Claude interface
You can now chat with Claude to query your Memgraph database

Available Tools

run_query()

This tool allows you to execute Cypher queries against your Memgraph database. Example usage in Claude:

Please run the query: MATCH (n) RETURN n LIMIT 10

Available Resources

get_schema()

This resource provides information about your Memgraph database schema, including node labels, relationship types, and properties. This helps the LLM understand your data model.

Note: This requires the --schema-info-enabled=True configuration flag when starting Memgraph.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.