Memory MCP Server
by jcdiv47
Memory MCP Server is a Python implementation of an MCP server designed to process and save memory as a knowledge graph. It allows AI systems to store, retrieve, and query structured data in the form of entities, relations, and observations, enabling information recall across sessions.
Last updated: N/A
What is Memory MCP Server?
MCP Server Memory is a Python server that maintains a persistent knowledge graph for AI memory. It facilitates storing, retrieving, and querying structured data (entities, relations, observations) for AI systems.
How to use Memory MCP Server?
Install the server using uv or pip. Configure it for MCP clients like Claude or Cursor by adding the appropriate settings to their configuration files. Run the server using the command mcp-server-memory, optionally setting the MEMORY_FILE_PATH environment variable to customize the knowledge graph data storage location.
Key features of Memory MCP Server
Create and manage entities with structured information
Establish typed relations between entities
Add observations to existing entities
Delete entities, relations, and observations
Search nodes in the knowledge graph
Retrieve specific nodes by name
Use cases of Memory MCP Server
Persistent memory for AI agents
Knowledge base for chatbots
Contextual understanding in AI systems
Long-term information storage and retrieval
FAQ from Memory MCP Server
How do I install the server?
How do I install the server?
You can install the server using either uv add mcp-server-memory or pip install mcp-server-memory.
How do I configure the server for Claude or Cursor?
How do I configure the server for Claude or Cursor?
Add the server configuration to your Claude (claude_desktop_config.json) or Cursor (mcp.json) settings file, specifying the command and arguments to run the server.
Where is the knowledge graph data stored?
Where is the knowledge graph data stored?
By default, the data is stored in a memory.json file in the package directory. You can customize the location using the MEMORY_FILE_PATH environment variable.
What is the MCP interface?
What is the MCP interface?
The MCP (Model Control Protocol) interface exposes tools for interacting with the knowledge graph, such as creating entities and relations, adding observations, and searching for nodes.
How do I contribute to the project?
How do I contribute to the project?
Clone the repository, install development dependencies, and submit pull requests with your changes.