Memory Bank MCP server

Memory Bank MCP is a structured documentation system that helps teams create, manage, and access project knowledge through the Model Context Protocol. It generates and maintains interconnected Markdown documents capturing different aspects of your project, from high-level goals to technical details and daily progress.

Installation

To install Memory Bank MCP, follow these steps:

# Clone the repository
git clone https://github.com/tuncer-byte/memory-bank-mcp.git
cd memory-bank-mcp

# Install dependencies
npm install

# Create .env file with your Gemini API key (optional)
echo "GEMINI_API_KEY=your_api_key_here" > .env

Running the Server

Development Mode

# Start in development mode
npm run dev

Production Mode

# Build the project
npm run build

# Start in production mode
npm run start

MCP Configuration

To integrate Memory Bank with the Model Context Protocol, add the following configuration to your mcp.json file:

{
  "memoryBank": {
    "command": "node",
    "args": ["/path/to/memory-bank-mcp/dist/index.js"],
    "env": {
      "GEMINI_API_KEY": "your_gemini_api_key_here"
    }
  }
}

Replace /path/to/memory-bank-mcp/dist/index.js with the absolute path to your built index.js file, and add your Gemini API key if applicable.

Example Configuration

{
  "memoryBank": {
    "command": "node",
    "args": ["/Users/username/memory-bank-mcp/dist/index.js"],
    "env": {
      "GEMINI_API_KEY": "AIzaSyXXXXXXXXXXXXXXXXXXXXXXXX"
    }
  }
}

Available MCP Tools

Memory Bank provides several tools via the Model Context Protocol:

Initialize Memory Bank

Creates a new Memory Bank structure with all document templates.

Parameters:

• goal (string): Project goal description (min 10 characters)
• geminiApiKey (string, optional): Gemini API key for document generation
• location (string, optional): Absolute path where memory-bank folder will be created

Example:

await callTool({
  name: "initialize_memory_bank",
  arguments: {
    goal: "Building a self-documenting AI-powered software development assistant",
    location: "/Users/username/Documents/projects/ai-assistant"
  }
});

Update Document

Updates a specific document in the Memory Bank.

Parameters:

• documentType (enum): One of: projectbrief, productContext, systemPatterns, techContext, activeContext, progress
• content (string, optional): New content for the document
• regenerate (boolean, default: false): Whether to regenerate the document using AI

Example:

await callTool({
  name: "update_document",
  arguments: {
    documentType: "projectbrief",
    content: "# Project Brief\n\n## Purpose\nTo develop an advanced and user-friendly AI..."
  }
});

Query Memory Bank

Searches across all documents with context-aware relevance ranking.

Parameters:

• query (string): Search query (min 5 characters)

Example:

await callTool({
  name: "query_memory_bank",
  arguments: {
    query: "system architecture components"
  }
});

Export Memory Bank

Exports all Memory Bank documents.

Parameters:

• format (enum, default: "folder"): Export format, either "json" or "folder"
• outputPath (string, optional): Custom output path for the export

Example:

await callTool({
  name: "export_memory_bank",
  arguments: {
    format: "json",
    outputPath: "/Users/username/Documents/exports"
  }
});

Document Types

Memory Bank organizes project knowledge into six core document types:

1. Project Brief (projectbrief.md): Core document defining project objectives, scope, and vision
2. Product Context (productContext.md): Documents product functionality from a user perspective
3. System Patterns (systemPatterns.md): Establishes system architecture and component relationships
4. Tech Context (techContext.md): Specifies technology stack and implementation details
5. Active Context (activeContext.md): Tracks current tasks, open issues, and development focus
6. Progress (progress.md): Documents completed work, milestones, and project history

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.