MCP Memory Py

🚀 Knowledge Graph Memory Server

A basic implementation using a local knowledge graph to achieve persistent memory, enabling Claude to remember user information across different chats.

This is a Python port of the original reference server (version 0.6.3). I took this opportunity to refactor some code, mainly with the help of Cline and Claude Sonnet 3.5.

🚀 Quick Start

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:

{
  "name": "John_Smith",
  "entityType": "person",
  "observations": ["Speaks fluent Spanish"]
}

Relations

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

Example:

{
  "from": "John_Smith",
  "to": "Anthropic",
  "relationType": "works_at"
}

Observations

Observations are discrete pieces of information about entities. They:

• Are stored as strings
• Are attached to specific entities
• Can be added or modified independently
• Are used to record facts

💻 Usage Examples

Basic Usage

In Claude Desktop:

uv run pytest

Advanced Usage

For debugging with MCP Inspector:

npx @modelcontextprotocol/inspector uv run --directory src -m mcp_memory_py

📚 Documentation

API Functions

create_entity

Create a new entity.

Parameters:

• entity_type (str): The type of the entity (e.g., "person", "organization")
• name (str): The name of the entity

Returns:

• The newly created entity object

add_relation

Add a relation to the knowledge graph.

Parameters:

• from_entity (str): The ID of the entity at the start of the relation
• to_entity (str): The ID of the entity at the end of the relation
• relation_type (str): The type of the relation (e.g., "works_at", "located_at")

add_observation

Add an observation to the knowledge graph.

Parameters:

• entity_id (str): The ID of the entity to which the observation belongs
• observation (str): The content of the observation

📄 License

This MCP server is released 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 refer to the LICENSE file in the project repository.