Memgraph MCP Server Integration

What does “Memgraph” MCP Server do?

Memgraph MCP Server is a lightweight implementation of the Model Context Protocol (MCP) designed to bridge the gap between Memgraph, a graph database, and large language models (LLMs). By exposing Memgraph’s data, schema, and query capabilities as MCP resources and tools, this server allows AI assistants to interact with graph data in real time. Developers can use it to perform database queries, extract schema information, and facilitate AI-driven workflows that require access to connected data stored in Memgraph. This integration streamlines building intelligent agents and applications that leverage graph-powered insights, making tasks such as querying, data exploration, and schema discovery more accessible and standardized within LLM ecosystems.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

• get_schema()
  Retrieves Memgraph schema information. This resource enables AI clients to understand the structure and types of data present in Memgraph, which is essential for generating accurate queries and responses. (Requires Memgraph to run with --schema-info-enabled=True.)

List of Tools

• run_query()
  Executes a Cypher query against the Memgraph database. This tool allows LLMs and AI agents to interact directly with the graph database, enabling dynamic data retrieval, analytics, and manipulation through AI-driven workflows.

Use Cases of this MCP Server

• Chat with the Database
  Users can interact conversationally with the Memgraph database, leveraging LLMs to compose, execute, and interpret Cypher queries for graph data exploration and analysis.

• Schema Discovery
  AI agents can automatically retrieve and understand the structure of the Memgraph database, simplifying the process of generating valid queries and integrating with new or evolving data models.

• Database Management
  Developers can use LLMs to help manage and query graph data, making it easier to perform administrative or analytical tasks without deep Cypher expertise.

• Integration with AI Workflows
  The server can be incorporated into AI-driven applications or platforms (like Claude) to provide real-time graph database access within larger intelligent workflows.

How to set it up

Windsurf

No setup instructions available for Windsurf.

Claude

1. Install Claude for Desktop.
2. Locate your Claude configuration file:
   • MacOS/Linux: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: $env:AppData\Claude\claude_desktop_config.json
3. Add the Memgraph MCP Server entry in the mcpServers object:

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

4. Save the configuration and restart Claude Desktop.
5. Verify that Memgraph tools and resources are listed in Claude.

Note: Use the absolute path for the uv executable. Obtain it with which uv (MacOS/Linux) or where uv (Windows).

Cursor

No setup instructions available for Cursor.

Cline

No setup instructions available for Cline.

Securing API Keys

No mention of securing API keys or usage of environment variables in the available documentation.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "memgraph": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “memgraph” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots Support: Not specified
Sampling Support: Not specified

Between the available setup, clear tool/resource description, and absence of prompts, roots, and sampling references, the Memgraph MCP Server is relatively basic but functional. It scores better for clarity and open source presence, though lacks advanced MCP features.

Our opinion

Based on the two tables, the Memgraph MCP Server scores a 5/10. It offers basic but well-documented MCP integration for Memgraph with working tools and resources, but lacks prompt templates, advanced features (roots, sampling), and broader multi-platform setup instructions.

MCP Score