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

Automatic Installation via Smithery

To automatically install the memory cache server for Claude Desktop via Smithery:

npx -y @smithery/cli install @tosin2013/mcp-memory-cache-server --client claude

Manual Installation

1. Clone the repository:

git clone https://github.com/tosin2013/mcp-memory-cache-server.git
cd mcp-memory-cache-server

2. Install dependencies:

npm install

3. Build the project:

npm run build

⚙️ Configuration

Using a Configuration File

Create a config.json file with the following content:

{
  "max_entries": 1000,
  "max_memory": 104857600, // 100MB
  "default_ttl": 3600,     // 1 hour
  "check_interval": 60000,  // 1 minute
  "stats_interval": 120000  // 2 minutes
}

Environment Variable Configuration

You can set environment variables in the MCP client section of package.json:

{
  "mcpServers": {
    "memory-cache": {
      "command": "node",
      "args": ["dist/index.js"],
      "env": {
        "MAX_ENTRIES": "5000",
        "MAX_MEMORY": "209715200", // 200MB
        "DEFAULT_TTL": "7200",     // 2 hours
        "CHECK_INTERVAL": "360000"  // 1 hour
      }
    }
  }
}

The server will:

1. Look for the default config.json file.
2. Apply any environment variable overrides.
3. Use default values if not specified.

✨ Features

Data Storage and Retrieval

• Automatically store data when it is first encountered.
• Provide data when a cache is available.

Automatic Cleanup Policy

• Remove old or infrequently used entries based on settings.
• Monitor memory usage to avoid exceeding limits.

💡 Usage Tip

Set an Appropriate TTL (Time-to-Live)

• Use a shorter TTL for frequently changing data.
• Use a longer TTL for static content.

Adjust Memory Limits

• A higher memory limit means more caching and more token savings.
• Lower the memory limit if memory usage is an issue.

Monitor Cache Statistics

• A high hit rate indicates good token savings.
• Adjust the TTL or limits when the hit rate is low.

💻 Usage Examples

Cache Testing in Practice

To observe the effects of caching, try the following scenarios:

File Reading Test

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

Data Analysis Test

• Perform some data analysis tasks.
• Request the same analysis results again.
• The second analysis will use the cached results and thus be faster.

Project Navigation Test

• Explore the project 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 observe:

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