Memory

servers

What is servers?

The servers project provides a basic implementation of persistent memory using a local knowledge graph. It allows AI models, specifically mentioning Claude, to remember information about users across different chat sessions. The core of the project revolves around managing entities, relations, and observations within a knowledge graph structure.

How to use servers?

To use the servers project, you can integrate it into your Claude Desktop configuration. This involves adding a JSON block to your claude_desktop_config.json file, specifying either Docker or NPX as the command to run the memory server.

Docker Setup:

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

NPX Setup:

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

You can also configure the memory storage path using environment variables. For VS Code integration, one-click installation buttons are provided for both VS Code and VS Code Insiders, supporting both NPX and Docker installations.

A system prompt example is provided for chat personalization, guiding the AI on how to identify users, retrieve and update memory during conversations.

Key Features of servers

• Knowledge Graph: Stores information as entities, relations, and observations.
  • Entities: Nodes with a unique name, type, and observations.
  • Relations: Directed connections between entities (e.g., "works_at").
  • Observations: Atomic facts stored as strings, attached to entities.
• API Endpoints: Provides tools for managing the knowledge graph:
  • create_entities, create_relations, add_observations
  • delete_entities, delete_observations, delete_relations
  • read_graph, search_nodes, open_nodes
• Integration: Supports integration with Claude Desktop via Docker or NPX.
• VS Code Integration: Offers one-click installation for VS Code and VS Code Insiders.
• Customization: Allows configuration of memory storage path and system prompts for AI behavior.

Use Cases of servers

• Chat Personalization: Enables AI models to remember user preferences, history, and basic identity across conversations, leading to more personalized interactions.
• Persistent Memory: Acts as a persistent memory store for AI agents, allowing them to build context and recall information over time.
• Information Management: Provides a structured way to store and retrieve information related to users, organizations, events, and their relationships.

FAQ from servers

Q1: How is information stored in the knowledge graph? A1: Information is stored using three main components: Entities (nodes with names and types), Relations (directed links between entities), and Observations (specific facts attached to entities).

Q2: What are the available API operations? A2: The available operations include creating/deleting entities, relations, and observations, as well as reading the entire graph, searching for nodes, and retrieving specific nodes.

Q3: How can I integrate this memory server with Claude Desktop? A3: You can integrate it by adding a specific JSON configuration to your claude_desktop_config.json file, choosing between Docker or NPX for running the server.

Q4: Can I customize where the memory is stored? A4: Yes, you can specify a custom path for memory storage using the MEMORY_FILE_PATH environment variable.

Q5: What kind of information should be stored as observations? A5: Observations should be atomic facts about an entity, such as "Speaks fluent Spanish" or "Graduated in 2019".

Building servers

Docker build command: ```sh docker build -t mcp/memory -f src/memory/Dockerfile . ```

License

The MCP server is licensed under the MIT License.

Knowledge Graph Memory Server

A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.

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 active voice and describe how entities interact or relate to each other.

Example:

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

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:

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

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

Usage with Claude Desktop

Setup

Add this to your claude_desktop_config.json:

Docker

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

NPX

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

NPX with custom setting

The server can be configured using the following environment variables:

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

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

VS Code Installation Instructions

For quick installation, use one of the one-click installation buttons below:

For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open Settings (JSON).

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.

NPX

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

Docker

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

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 chat personalization. You could use this prompt in the "Custom Instructions" field of a Claude.ai Project.

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
     c) Store facts about them as observations

Building

Docker:

docker build -t mcp/memory -f src/memory/Dockerfile . 

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.