Knowledge Graph Memory Server

A basic implementation of persistent memory using a local knowledge graph powered by Kuzu embedded graph database.

Core Concepts

Entities

Entities are the primary nodes in the knowledge graph. Each entity has:

• A unique name (identifier)

• An entity type (e.g., "person", "organization", "event")

• A list of observations

Example:

Relations

Relations define directed connections between entities. They are always stored in active voice and describe how entities interact or relate to each other.

Example:

Observations

Observations are discrete pieces of information about an entity. They are:

• Stored as strings

• Attached to specific entities

• Can be added or removed independently

• Should be atomic (one fact per observation)

Example:

Tags

Tags provide a flexible way to categorize and organize entities and observations. They enable:

• Cross-cutting classification of entities and observations

• Easy filtering and discovery of related information

• Hierarchical organization with optional categories

• Metadata storage with descriptions

Example:

Tags can be applied to:

• Entities: For categorizing people, projects, concepts, etc.

• Observations: For marking specific facts with metadata like confidence, source, or relevance

API

Tools

• create_entities

  • Create multiple new entities in the knowledge graph

  • Input: entities (array of objects)

    • Each object contains:

      • name (string): Entity identifier

      • entityType (string): Type classification

      • observations (string[]): Associated observations

  • Ignores entities with existing names

• create_relations

  • Create multiple new relations between entities

  • Input: relations (array of objects)

    • Each object contains:

      • from (string): Source entity name

      • to (string): Target entity name

      • relationType (string): Relationship type in active voice

  • Skips duplicate relations

• add_observations

  • Add new observations to existing entities

  • Input: observations (array of objects)

    • Each object contains:

      • entityName (string): Target entity

      • contents (string[]): New observations to add

  • Returns added observations per entity

  • Fails if entity doesn't exist

• delete_entities

  • Remove entities and their relations

  • Input: entityNames (string[])

  • Cascading deletion of associated relations

  • Silent operation if entity doesn't exist

• delete_observations

  • Remove specific observations from entities

  • Input: deletions (array of objects)

    • Each object contains:

      • entityName (string): Target entity

      • observations (string[]): Observations to remove

  • Silent operation if observation doesn't exist

• delete_relations

  • Remove specific relations from the graph

  • Input: relations (array of objects)

    • Each object contains:

      • from (string): Source entity name

      • to (string): Target entity name

      • relationType (string): Relationship type

  • Silent operation if relation doesn't exist

• read_graph

  • Read the entire knowledge graph

  • No input required

  • Returns complete graph structure with all entities and relations

• search_nodes

  • Search for nodes based on query

  • Input: query (string)

  • Searches across:

    • Entity names

    • Entity types

    • Observation content

  • Returns matching entities and their relations

• open_nodes

  • Retrieve specific nodes by name

  • Input: names (string[])

  • Returns:

    • Requested entities

    • Relations between requested entities

  • Silently skips non-existent nodes

• tag_entity

  • Add tags to entities

  • Input: entityName (string), tagNames (string[])

  • Creates tags if they don't exist

  • Returns array of successfully added tags

• tag_observation

  • Add tags to specific observations

  • Input: entityName (string), observationContent (string), tagNames (string[])

  • Creates tags if they don't exist

  • Returns array of successfully added tags

• get_entities_by_tag

  • Find entities with a specific tag

  • Input: tagName (string)

  • Returns entities and their relations that have the specified tag

• get_all_tags

  • List all available tags

  • No input required

  • Returns all tags with their categories and descriptions

• get_tag_usage

  • Get usage statistics for tags

  • No input required

  • Returns tag usage counts for entities and observations

• remove_tags_from_entity

  • Remove specific tags from an entity

  • Input: entityName (string), tagNames (string[])

  • Returns array of successfully removed tags

Usage

Setup

Add this to your mcp server config:

NPX

The database file will be created automatically if it doesn't exist. Choose a location where you want to persistently store your knowledge graph data.

VS Code Configuration

Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.

Note that the mcp key is not needed in the .vscode/mcp.json file.

Usage Examples

Basic Entity and Relation Management

Discovery and Organization

System Prompt

The prompt for utilizing memory depends on the use case. Changing the prompt will help the model determine the frequency and types of memories created.

Here is an example prompt for project context management with tagging.

Building

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.