Charly Memory Cache

🚀 Memory Cache Server

A Model Context Protocol (MCP) server that reduces token consumption by efficiently caching data between language model interactions. It is suitable for any MCP client and any language model that uses tokens.

🚀 Quick Start

📦 Installation

1. Clone the repository:

git clone git@github.com:ibproduct/ib-mcp-cache-server
cd ib-mcp-cache-server

2. Install dependencies:

npm install

3. Build the project:

npm run build

4. Add it to your MCP client settings:

{
  "mcpServers": {
    "memory-cache": {
      "command": "node",
      "args": ["/path/to/ib-mcp-cache-server/build/index.js"]
    }
  }
}

5. The server will start automatically when using the MCP client.

✅ Verify Its Proper Operation

When the server is running properly, you will see:

1. A message in the terminal: "Memory cache MCP server is running on stdio"
2. Performance improvement when accessing the same data multiple times
3. You don't need to do anything - caching is automatic

You can verify if the server is running by:

1. Opening your MCP client
2. Looking for any error messages in the terminal where the server was started
3. Performing operations that can benefit from caching (e.g., reading the same file multiple times)

🛠️ Configuration

Configure via config.json or environment variables:

{
  "maxEntries": 1000,        // Maximum number of stored items is 1000
  "maxMemory": 104857600,    // Maximum memory usage in bytes (100MB)
  "defaultTTL": 3600,        // Default time-to-live in seconds (1 hour)
  "checkInterval": 60000,    // Cleanup interval in milliseconds (1 minute)
  "statsInterval": 30000     // Statistics update interval in milliseconds (30 seconds)
}

📋 Configuration Option Explanation

1. maxEntries (Default: 1000)

   • The maximum number of items that can be stored in the cache
   • Prevents the cache from growing indefinitely
   • When the limit is exceeded, the least recently used item is removed first

2. maxMemory (Default: 100MB)

   • The maximum memory usage in bytes
   • Prevents excessive memory consumption
   • When the limit is reached, the least recently used item is removed

3. defaultTTL (Default: 3600)

   • The default time-to-live in seconds
   • Controls the expiration time of cache items

4. checkInterval (Default: 60000)

   • The cleanup check interval in milliseconds
   • The time interval for periodically cleaning up expired caches

5. statsInterval (Default: 30000)

   • The statistics update interval in milliseconds
   • The frequency of updating cache statistics

💻 Usage Examples

🧐 Test the Actual Effect of the Cache

To observe the cache in action, try the following scenarios:

📄 File Reading Test

• Read and analyze a large file
• Ask the same question about the file again
• The second response should be faster because the file content is cached

📊 Data Analysis Test

• Perform a certain data analysis
• Request the same analysis result again
• The second analysis will use the cached result

📂 Project Navigation Test

• Explore the project's structure
• Query the same file/directory again
• The directory list and file content will be provided from the cache

The cache is working when you notice:

• Faster response times for repeated operations
• Consistent answers for unchanged content
• No need to re-read unchanged files