What is Memory Bank MCP Server

The Memory Bank MCP Server is a centralized service that allows for the management of memory bank files over the Model Context Protocol (MCP). It transforms traditional file-based storage into a remote-access solution that supports multiple projects while maintaining a consistent file structure and validation.

Use cases

Use cases include managing memory banks for various AI projects, enabling teams to share and collaborate on memory resources. It’s particularly useful for organizations that require isolated memory banks for different projects, ensuring security and proper access control.

How to use

To use the Memory Bank MCP Server, install it via the Smithery CLI or manually configure it in your MCP settings file. Adjust the settings to specify the memory bank’s root directory, enable the server, and define operations that can automatically be approved before starting to use memory bank tools in your AI assistant.

Key features

Key features of the Memory Bank MCP Server include support for multiple projects with defined directories, remote accessibility via a full MCP implementation, type-safe operations, project isolation, and various core operations like reading, writing, and updating memory bank files, as well as listing projects and their files.

Where to use

The server can be used in AI applications requiring memory management and organization, specifically in environments using platforms like Cline, Claude, or Cursor. It is suitable for both desktop applications and development setups using Docker.

Memory Bank MCP Server

A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.

Overview

The Memory Bank MCP Server transforms traditional file-based memory banks into a centralized service that:

• Provides remote access to memory bank files via MCP protocol
• Enables multi-project memory bank management
• Maintains consistent file structure and validation
• Ensures proper isolation between project memory banks

Features

• Multi-Project Support

  • Project-specific directories
  • File structure enforcement
  • Path traversal prevention
  • Project listing capabilities
  • File listing per project

• Remote Accessibility

  • Full MCP protocol implementation
  • Type-safe operations
  • Proper error handling
  • Security through project isolation

• Core Operations

  • Read/write/update memory bank files
  • List available projects
  • List files within projects
  • Project existence validation
  • Safe read-only operations

Installation

To install Memory Bank Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @alioshr/memory-bank-mcp --client claude

This will set up the MCP server configuration automatically. Alternatively, you can configure the server manually as described in the Configuration section below.

Quick Start

1. Configure the MCP server in your settings (see Configuration section below)
2. Start using the memory bank tools in your AI assistant

Configuration

The memory bank MCP server needs to be configured in your Cline MCP settings file. The location depends on your setup:

• For Cline extension: ~/Library/Application Support/Cursor/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
• For Roo Code VS Code extension: ~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/mcp_settings.json
• For Claude desktop app: ~/Library/Application Support/Claude/claude_desktop_config.json

Add the following configuration to your MCP settings:

{
  "allpepper-memory-bank": {
    "command": "npx",
    "args": [
      "-y",
      "@allpepper/memory-bank-mcp"
    ],
    "env": {
      "MEMORY_BANK_ROOT": "<path-to-bank>"
    },
    "disabled": false,
    "autoApprove": [
      "memory_bank_read",
      "memory_bank_write",
      "memory_bank_update",
      "list_projects",
      "list_project_files"
    ]
  }
}

Configuration Details

• MEMORY_BANK_ROOT: Directory where project memory banks will be stored (e.g., /path/to/memory-bank)
• disabled: Set to false to enable the server
• autoApprove: List of operations that don’t require explicit user approval:
  • memory_bank_read: Read memory bank files
  • memory_bank_write: Create new memory bank files
  • memory_bank_update: Update existing memory bank files
  • list_projects: List available projects
  • list_project_files: List files within a project

For Cursor

For Cursor, open the settings -> features -> add MCP server -> add the following:

env MEMORY_BANK_ROOT=<path-to-bank> npx -y @allpepper/memory-bank-mcp@latest

Custom IA instructions

This section contains the instructions that should be pasted on the AI custom instructions, either for Cline, Claude or Cursor, or any other MCP client. You should copy and paste these rules. For reference, see custom-instructions.md which contains these rules.

Development

Basic development commands:

# Install dependencies
npm install

# Build the project
npm run build

# Run tests
npm run test

# Run tests in watch mode
npm run test:watch

# Run the server directly with ts-node for quick testing
npm run dev

Running with Docker

1. Build the Docker image:

   docker build -t memory-bank-mcp:local .
   

2. Run the Docker container for testing:

   docker run -i --rm \
     -e MEMORY_BANK_ROOT="/mnt/memory_bank" \
     -v /path/to/memory-bank:/mnt/memory_bank \
     --entrypoint /bin/sh \
     memory-bank-mcp:local \
     -c "ls -la /mnt/memory_bank"
   

3. Add MCP configuration, example for Roo Code:

Contributing

Contributions are welcome! Please follow these steps:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

Development Guidelines

• Use TypeScript for all new code
• Maintain type safety across the codebase
• Add tests for new features
• Update documentation as needed
• Follow existing code style and patterns

Testing

• Write unit tests for new features
• Include multi-project scenario tests
• Test error cases thoroughly
• Validate type constraints
• Mock filesystem operations appropriately

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

This project implements the memory bank concept originally documented in the Cline Memory Bank, extending it with remote capabilities and multi-project support.