MCP Server: Memory
by kwanLeeFrmVi
An MCP server providing persistent memory capabilities for AI models through a knowledge graph. It allows models like Claude to retain and recall information across interactions.
Last updated: N/A
What is MCP Server: Memory?
This server implements the Model Context Protocol and acts as a bridge between an AI model and a persistent knowledge graph stored locally. It enables the AI model to create, manage, and relate entities, store observations, and retrieve information.
How to use MCP Server: Memory?
The server is designed to be used with MCP-compatible clients like the Claude Desktop application. Configure it within the client's settings by specifying the command and arguments to run the server, along with any necessary environment variables like the memory file path.
Key features of MCP Server: Memory
Create and manage entities
Define relationships between entities
Store observations associated with entities
Search and retrieve information from the knowledge graph
Use cases of MCP Server: Memory
Allowing AI models to remember past interactions
Building a knowledge base for AI models
Enabling AI models to reason about relationships between entities
Providing AI models with persistent context
FAQ from MCP Server: Memory
What is MCP?
What is MCP?
Model Context Protocol, a protocol for AI models to interact with external data sources.
Where is the knowledge graph stored?
Where is the knowledge graph stored?
By default, in a knowledge_graph.json file in the current working directory.
Can I customize the storage location?
Can I customize the storage location?
Yes, you can specify a custom file path using the MEMORY_FILE_PATH environment variable.
What AI models are compatible?
What AI models are compatible?
The server is designed to work with MCP-compatible clients like the Claude Desktop application.
How do I start the server?
How do I start the server?
Using a command like npx mcp-server-memory.