MCP.so
登录

Memory Cache Server

@MCP-Mirror

代码仓库

关于 Memory Cache Server

Mirror of

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

基本信息

分类

记忆与知识

运行时

node

传输方式

stdio

发布者

MCP-Mirror

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

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.

评论

记忆与知识 分类下的更多 MCP 服务器

MCP server for Obsidian

MarkusPfundstein

MCP server that interacts with Obsidian via the Obsidian rest API community plugin

4.0K

Anytype MCP Server

anyproto

An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.

467

Notion MCP Integration

danhilse

A simple MCP integration that allows Claude to read and manage a personal Notion todo list

208

JupyterMCP - Jupyter Notebook Model Context Protocol Integration

jjsantos01

A Model Context Protocol (MCP) for Jupyter Notebook

130

Ultimate Google Docs & Drive MCP Server

a-bonus

The Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.

605