Memory Cache Server

@MCP-Mirror

About Memory Cache Server

Mirror of

#memory-cache #mcp-server #token-reduction

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Memory Cache Server?

Memory Cache Server is a Model Context Protocol (MCP) server that reduces token consumption by automatically caching data between language model interactions. It works with any MCP client and any language model that uses tokens.

How to use Memory Cache Server?

Install by cloning the repository, running npm install and npm run build. Add the server to your MCP client settings using the command "node" and args pointing to build/index.js. The server starts automatically with your client and caches data without further action.

Key features of Memory Cache Server

Automatic caching of data between interactions
Configurable maximum cache entries (default 1000)
Configurable maximum memory usage (default 100MB)
Time-to-live (TTL) for cached items (default 1 hour)
Configurable cleanup and stats update intervals
Monitor cache effectiveness through hit/miss statistics

Use cases of Memory Cache Server

Repeated file reading: cache file content to avoid re-sending tokens
Repeated computations: cache results of analysis or calculations
Frequent data access: serve cached data for the same queries until TTL expires
Project navigation: cache directory listings and file contents

FAQ from Memory Cache Server

What data does the cache store?

The cache stores file content, computation results, and any frequently accessed data that would otherwise need to be re-sent.

How does it reduce token consumption?

By storing data when first encountered and serving it from cache on subsequent requests, avoiding the need to re-transmit the same information.

Does it work with any language model?

Yes, it works with any language model that uses tokens, as long as you connect through an MCP client.

How do I configure the cache?

You can set maxEntries, maxMemory, defaultTTL, checkInterval, and statsInterval via config.json or environment variables (MAX_ENTRIES, MAX_MEMORY, etc.).

How can I verify the cache is working?

Look for faster responses on repeated operations, consistent answers about unchanged content, and no need to re-read files. The server prints "Memory Cache MCP server running on stdio" when started.

Frequently asked questions