memory-mcp-server

memory-mcp-server

3.6

If you are the rightful owner of memory-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

A Model Context Protocol server that provides knowledge graph management capabilities, enabling LLMs to maintain memory across conversations.

The Memory MCP Server is a Swift implementation of a Model Context Protocol server designed to manage knowledge graphs. It allows large language models (LLMs) to create, read, update, and delete entities and relations within a persistent knowledge graph. This capability is crucial for AI assistants to maintain memory across conversations, ensuring continuity and context retention. The server supports macOS 14.0 or later, with a Go language implementation available for broader platform support. It features a robust system for managing entities and their relationships, tracking observations over time, and performing powerful searches within the knowledge graph. The data is stored persistently in a JSON format, allowing for easy retrieval and management.

Features

  • Knowledge Graph Storage: Maintain a persistent graph of entities and their relationships.
  • Entity Management: Create, retrieve, update, and delete entities with custom types.
  • Relation Tracking: Define and manage relationships between entities in active voice.
  • Observation System: Add and remove observations about entities over time.
  • Powerful Search: Find relevant nodes by name, type, or observation content.

Tools

  1. create_entities

    Create multiple new entities in the knowledge graph.

  2. create_relations

    Create multiple new relations between entities.

  3. add_observations

    Add new observations to existing entities.

  4. delete_entities

    Delete multiple entities and their associated relations.

  5. delete_observations

    Delete specific observations from entities.

  6. delete_relations

    Delete multiple relations from the knowledge graph.

  7. read_graph

    Read the entire knowledge graph.

  8. search_nodes

    Search for nodes in the knowledge graph based on a query.

  9. open_nodes

    Open specific nodes in the knowledge graph by their names.