Memory Custom

🚀 Custom Memory Server (Memory Custom)

This project adds new features to the memory server provided by the MCP team. It allows users to create and manage a knowledge graph for capturing interactions via large language models (LLMs).

✨ Features

1. Custom Memory Path

• Users can now specify different memory file paths for different projects.
• Why? This feature enhances the ability to organize and manage memory data, allowing users to store data by project.

2. Timestamp Recording

• The server now generates timestamps for interactions.
• Why? Timestamps make it possible to track the creation or modification time of each memory, providing better context and history.

🚀 Quick Start

Prerequisites

• Node.js (version 16 or higher)

Installation via Smithery

Automatically install the knowledge graph memory server for Claude Desktop through Smithery:

npx -y @smithery/cli install @BRO3886/mcp-memory-custom --client claude

Installation

1. Clone the repository:

   git clone git@github.com:BRO3886/mcp-memory-custom.git
   cd mcp-memory-custom
   

2. Install dependencies:

   npm install
   

Configuration

Before running the server, you can set the MEMORY_FILE_PATH environment variable to specify the path of the memory file. If not set, by default, the server will use memory.json in the same directory as the script.

Run the Server

Update the mcp Server JSON File

Add the following content to your claude_desktop_config.json / .cursor/mcp.json file:

{
  "mcpServers": {
    "memory": {
      "command": "node",
      "args": ["/path/to/mcp-memory-custom/dist/index.js"]
    }
  }
}

System prompt changes:

Follow these steps for each interaction:
1. The memory file path for this project is /path/to/memory/project_name.json - Always pass this path in all memory file operations (e.g., creating entities, relationships, or retrieving memories).
2. User identification:
   - Assume you are interacting with default_user.
   - If default_user is not yet identified, actively try to do so.

3. Memory retrieval:
   - Always start with “Remembering...”, only reply with “Remembering...”, and then retrieve all relevant information from your knowledge graph.
   - Always refer to your knowledge graph as “memory”.

4. Memory content:
   - When communicating with the user, pay attention to any new information belonging to the following categories:
     a) Basic personality (age, gender, location, position, education level, etc.)
     b) Behavior (interests, habits, etc.)
     c) Preferences (communication style, preferred language, etc.)
     d) Other relevant information.

5. Memory management:
   - Ensure that all memory content is clear, accurate, and relevant to the current conversation.
   - Avoid including irrelevant or duplicate information.

6. Response format:
   - Use clear and concise language for replies.
   - In complex situations, list information point by point to improve readability.

Command to Run the Server

Run the following command in the terminal to start the server:

npm start

📚 Documentation

API Endpoints

Create a Knowledge Graph

To create a new knowledge graph, send a POST request to:

http://localhost:3000/create-graph

Request body:

{
  "graphName": "string", // Name of the knowledge graph
  "description": "string" // Optional, description of the knowledge graph
}

Query a Knowledge Graph

To query information from an existing knowledge graph, send a POST request to:

http://localhost:3000/query-graph

Request body:

{
  "graphName": "string", // Name of the knowledge graph
  "query": "string" // Specific content of the query
}

Update a Knowledge Graph

To update information in an existing knowledge graph, send a PUT request to:

http://localhost:3000/update-graph

Request body:

{
  "graphName": "string", // Name of the knowledge graph
  "updates": { // Content to be updated
    "property1": "new value 1",
    "property2": "new value 2"
  }
}

Delete a Knowledge Graph

To delete an existing knowledge graph, send a DELETE request to:

http://localhost:3000/delete-graph

Request body:

{
  "graphName": "string" // Name of the knowledge graph to be deleted
}

💻 Usage Examples

Create a New Knowledge Graph

Send the following POST request:

curl -X POST http://localhost:3000/create-graph \
-H "Content-Type: application/json" \
-d '{"graphName":"User Information Graph","description":"Store user-related information"}'

Query a Knowledge Graph

Send the following POST request:

curl -X POST http://localhost:3000/query-graph \
-H "Content-Type: application/json" \
-d '{"graphName":"User Information Graph","query":"Query the user's age and location"}'

Update a Knowledge Graph

Send the following PUT request:

curl -X PUT http://localhost:3000/update-graph \
-H "Content-Type: application/json" \
-d '{"graphName":"User Information Graph","updates":{"Age":"28","Location":"Beijing"}}'

Delete a Knowledge Graph

Send the following DELETE request:

curl -X DELETE http://localhost:3000/delete-graph \
-H "Content-Type: application/json" \
-d '{"graphName":"User Information Graph"}'

Conclusion

With this project, you can easily create, query, update, and delete knowledge graphs, enabling efficient interactive memory management.