Knowledge Graph Memory MCP server

The MCP Knowledge Graph Memory Server provides a persistent memory system for AI assistants using a local knowledge graph. This implementation allows Claude to remember information about users across conversations by storing entities, relations, and observations in a structured format.

Installation Options

Docker Setup

Add the following configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "memory": {
      "command": "docker",
      "args": ["run", "-i", "-v", "claude-memory:/app/dist", "--rm", "mcp/memory"]
    }
  }
}

NPX Setup

Alternatively, you can use NPX to run the server:

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

Custom Configuration

The server can be configured using environment variables:

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ],
      "env": {
        "MEMORY_FILE_PATH": "/path/to/custom/memory.json"
      }
    }
  }
}

Available configuration options:

• MEMORY_FILE_PATH: Path to the memory storage JSON file (default: memory.json in the server directory)

Using the Memory System

Knowledge Graph Structure

The memory system is built around three core concepts:

Entities

Entities are primary nodes in the knowledge graph with:

• A unique name identifier
• An entity type (e.g., "person", "organization")
• A list of observations

Example entity:

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

Relations

Relations define connections between entities:

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

Observations

Observations are individual facts about entities:

{
  "entityName": "John_Smith",
  "observations": [
    "Speaks fluent Spanish",
    "Graduated in 2019",
    "Prefers morning meetings"
  ]
}

Available API Tools

Creating and Managing Data

• create_entities: Add new entities to the graph
• create_relations: Define relationships between entities
• add_observations: Attach new observations to entities
• delete_entities: Remove entities and their relations
• delete_observations: Remove specific observations
• delete_relations: Remove relationships between entities

Retrieving Data

• read_graph: Get the entire knowledge graph
• search_nodes: Find entities based on search criteria
• open_nodes: Retrieve specific entities by name

Setting Up System Prompts

To effectively use the memory system, add instructions to Claude's system prompt. Here's an example for chat personalization:

Follow these steps for each interaction:

1. User Identification:
   - You should assume that you are interacting with default_user
   - If you have not identified default_user, proactively try to do so.

2. Memory Retrieval:
   - Always begin your chat by saying only "Remembering..." and retrieve all relevant information from your knowledge graph
   - Always refer to your knowledge graph as your "memory"

3. Memory
   - While conversing with the user, be attentive to any new information that falls into these categories:
     a) Basic Identity (age, gender, location, job title, education level, etc.)
     b) Behaviors (interests, habits, etc.)
     c) Preferences (communication style, preferred language, etc.)
     d) Goals (goals, targets, aspirations, etc.)
     e) Relationships (personal and professional relationships up to 3 degrees of separation)

4. Memory Update:
   - If any new information was gathered during the interaction, update your memory as follows:
     a) Create entities for recurring organizations, people, and significant events
     b) Connect them to the current entities using relations
     b) Store facts about them as observations

This prompt can be used in the "Custom Instructions" field of a Claude.ai Project.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.