`mcp-knowledge-graph`
Knowledge Graph Memory Server
An improved implementation of persistent memory using a local knowledge graph with a customizable
--memory-path.This lets AI models remember information about the user across chats. It works with any AI model that supports the Model Context Protocol (MCP) or function calling capabilities.
[!NOTE] This is a fork of the original Memory Server and is intended to not use the ephemeral memory npx installation method.
Server Name
screen-of-server-name
read-function
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:
API
Tools
- create_entities
- create_relations
- add_observations
- delete_entities
- delete_observations
- delete_relations
- read_graph
- search_nodes
- open_nodes
Usage with MCP-Compatible Platforms
This server can be used with any AI platform that supports the Model Context Protocol (MCP) or function calling capabilities, including Claude, GPT, Llama, and others.
Setup with Claude Desktop
Add this to your claude_desktop_config.json:
Setup with Other AI Platforms
Any AI platform that supports function calling or the MCP standard can connect to this server. The specific configuration will depend on the platform, but the server exposes standard tools through the MCP interface.
Custom Memory Path
You can specify a custom path for the memory file:
If no path is specified, it will default to memory.jsonl in the server's installation directory.
System Prompt
The prompt for utilizing memory depends on the use case and the AI model you're using. Changing the prompt will help the model determine the frequency and types of memories created.
Here is an example prompt for chat personalization that can be adapted for any AI model. For Claude users, you could use this prompt in the "Custom Instructions" field of a Claude.ai Project. For other models, adapt it to their respective instruction formats.
Integration with Other AI Models
This server implements the Model Context Protocol (MCP) standard, making it compatible with any AI model that supports function calling. The knowledge graph structure and API are model-agnostic, allowing for flexible integration with various AI platforms.
To integrate with other models:
- Configure the model to access the MCP server
- Ensure the model can make function calls to the exposed tools
- Adapt the system prompt to the specific model's instruction format
- Use the same knowledge graph operations regardless of the model
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.
`mcp-knowledge-graph`
Knowledge Graph Memory Server
An improved implementation of persistent memory using a local knowledge graph with a customizable
--memory-path.This lets AI models remember information about the user across chats. It works with any AI model that supports the Model Context Protocol (MCP) or function calling capabilities.
[!NOTE] This is a fork of the original Memory Server and is intended to not use the ephemeral memory npx installation method.
Server Name
screen-of-server-name
read-function
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:
API
Tools
- create_entities
- create_relations
- add_observations
- delete_entities
- delete_observations
- delete_relations
- read_graph
- search_nodes
- open_nodes
Usage with MCP-Compatible Platforms
This server can be used with any AI platform that supports the Model Context Protocol (MCP) or function calling capabilities, including Claude, GPT, Llama, and others.
Setup with Claude Desktop
Add this to your claude_desktop_config.json:
Setup with Other AI Platforms
Any AI platform that supports function calling or the MCP standard can connect to this server. The specific configuration will depend on the platform, but the server exposes standard tools through the MCP interface.
Custom Memory Path
You can specify a custom path for the memory file:
If no path is specified, it will default to memory.jsonl in the server's installation directory.
System Prompt
The prompt for utilizing memory depends on the use case and the AI model you're using. Changing the prompt will help the model determine the frequency and types of memories created.
Here is an example prompt for chat personalization that can be adapted for any AI model. For Claude users, you could use this prompt in the "Custom Instructions" field of a Claude.ai Project. For other models, adapt it to their respective instruction formats.
Integration with Other AI Models
This server implements the Model Context Protocol (MCP) standard, making it compatible with any AI model that supports function calling. The knowledge graph structure and API are model-agnostic, allowing for flexible integration with various AI platforms.
To integrate with other models:
- Configure the model to access the MCP server
- Ensure the model can make function calls to the exposed tools
- Adapt the system prompt to the specific model's instruction format
- Use the same knowledge graph operations regardless of the model
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.