Memory Graph is a graph database-based MCP server for AI agents. It stores and retrieves data as nodes and relationships, allowing agents to track connections between code, functions, and variables. It connects to Neo4j for graph storage and provides tools for querying and updating the graph. Developers use it to build agents that understand and manipulate code structure.
Memory Graph is a graph database-based MCP server for AI agents. It stores and retrieves data as nodes and relationships, allowing agents to track connections between code, functions, and variables. It connects to Neo4j for graph storage and provides tools for querying and updating the graph. Developers use it to build agents that understand and manipulate code structure.
pip install memory-graphAdd this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"memory-graph-memory-graph-github": {
"command": "uvx",
"args": [
"pip install memory-graph"
]
}
}
}Restart Claude Desktop, then ask:
"What tools do you have available from memory graph?"
No configuration required. This server works out of the box.
"What resources are available in memory graph?"
Claude will query available resources and return a list of what you can access.
"Show me details about [specific item] in memory graph"
Claude will fetch and display detailed information about the requested item.
"Create a new [item] in memory graph with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.