mcp-knowledge-graph
The mcp-knowledge-graph is a memory server that uses a local knowledge graph to maintain persistent memory for AI models. It is designed to store and manage information as entities, relations, and observations, making it ideal for platforms that utilize the Model Context Protocol.
What is the purpose of the mcp-knowledge-graph server?
The mcp-knowledge-graph server provides persistent memory capabilities for AI models by using a local knowledge graph to store and recall user information across chat sessions.
How does the server handle entity and relation management?
The server allows for the creation, deletion, and querying of entities and relations within the knowledge graph, enabling AI models to maintain context and personalize interactions.
Can I specify a custom path for the memory file?
Yes, you can specify a custom path for the memory file using the --memory-path option when setting up the server.
Is the server compatible with all AI models?
The server is compatible with any AI model that supports the Model Context Protocol (MCP) or function calling capabilities, allowing for integration with platforms like Claude, GPT, and Llama.
What happens if I try to delete a non-existent entity or observation?
The server performs silent operations for deletions, meaning it will not raise errors if you attempt to delete non-existent entities or observations.