Context Optimizer MCP

Name: Context Optimizer MCP
Author: degenhero

@degenhero

代码仓库

关于 Context Optimizer MCP

An MCP server that uses Redis and in-memory caching to optimize and extend context windows for large chat histories

#context-optimizer #mcp #chat-optimization

基本信息

分类

其他

运行时

node

传输方式

stdio

发布者

degenhero

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "context-optimizer-mcp": {
      "command": "npx",
      "args": [
        "mcp",
        "install",
        "degenhero/context-optimizer-mcp"
      ]
    }
  }
}

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 Context Optimizer MCP?

Context Optimizer MCP is an MCP server that uses Redis and in-memory caching to optimize and extend context windows for large chat histories. It acts as a middleware between your application and LLM providers (currently supporting Anthropic's Claude models), automatically summarizing older messages to stay within token limits while preserving key information.

How to use Context Optimizer MCP?

Install using the MCP client (npx mcp install degenhero/context-optimizer-mcp), manually via npm install, or with Docker (docker-compose up -d). Configure environment variables in .env (Anthropic API key, Redis host/port, caching settings). Start the server, then send HTTP POST requests to http://localhost:3000/v1/messages using the standard Anthropic API format, optionally including conversation_id and context_optimization parameters.

Key features of Context Optimizer MCP

Dual-layer caching: in-memory LRU and persistent Redis
Automatic context summarization when nearing token limit
Rate limiting with burst protection
Drop-in replacement for Anthropic API
Built-in performance monitoring and metrics collection
Conversation continuity via unique conversation_id

Use cases of Context Optimizer MCP

Extending context for long-running chatbot sessions
Managing large conversation histories within token limits
Reducing API costs by caching summarized contexts
Maintaining context across multiple API calls for complex interactions

FAQ from Context Optimizer MCP

What are the prerequisites?

Node.js 18+, a Redis server (local or remote), and an Anthropic API key.

How do I configure it?

Copy .env.example to .env and set ANTHROPIC_API_KEY, Redis host/port/password, and caching parameters (e.g., IN_MEMORY_CACHE_MAX_SIZE). The server listens on port 3000 by default.

Does it support other LLM providers?

Currently, only Anthropic's Claude models are supported.

What transport does it use?

The server exposes an HTTP endpoint at /v1/messages that is compatible with the Anthropic API. It also provides /health and /metrics endpoints.

Where are conversation histories stored?

Summarized contexts are cached in both an in-memory LRU cache (for fast access) and Redis (for persistent, distributed storage across server instances).