mcp-memory-domain-knowledge
If you are the rightful owner of mcp-memory-domain-knowledge 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 basic implementation of persistent memory using a local knowledge graph, allowing Claude to remember information about the user across chats.
The Knowledge Graph Memory Server is a model context protocol server that implements persistent memory using a local knowledge graph. It allows for the storage and retrieval of user information across different chat sessions, enabling a more personalized interaction experience. The server uses entities, relations, and observations to structure and manage data. Entities are the primary nodes, each with a unique identifier, type, and list of observations. Relations define how entities interact, while observations are discrete pieces of information attached to entities. The server provides a comprehensive API for creating, managing, and querying these components, ensuring efficient data handling and retrieval.
Features
- Entity Management: Create, delete, and manage entities with unique identifiers and associated observations.
- Relation Handling: Define and manage directed connections between entities to represent interactions.
- Observation Management: Add, remove, and query discrete pieces of information about entities.
- Graph Querying: Search and retrieve nodes and their relations based on keywords and entity names.
- Integration Flexibility: Supports Docker and NPX for easy setup and configuration.
Tools
create_entities
Create multiple new entities
create_relations
Create inter-entity relationships
add_observations
Add observation information to the entity
delete_entities
Delete entities and their associations
delete_observations
Delete specific observation information
delete_relations
Delete a specific relationship
read_graph
Read the entire knowledge graph
search_nodes
Search nodes based on keywords
open_nodes
Retrieve specific nodes by name
