広告掲載
MCP.so
ログイン
C

Context Rot Detection MCP Server

@milos-product-maker

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

milos-product-maker

投稿者

Miloš Borenović

Context Rot Detection MCP Server について

Context Rot Detection & Healing — gives AI agents self-awareness about their cognitive state by analyzing token utilization, quality degradation, and session fatigue. Returns health scores (0-100), model-specific degradation curves for 15+ models, lost-in-the-middle risk scoring,

#mcp#context-rot#ai-agents#context-window#agent-health#llm#context-engineering#model-context-protocol

Context Rot Detection MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "context-rot-detection": {
      "command": "npx",
      "args": [
        "-y",
        "context-rot-detection"
      ],
      "env": {
        "HEALTH_HISTORY_DB": "./health.db"
      }
    }
  }
}

Context Rot Detection MCP Server のツール

3

Analyze your current context window health. Returns a health score (0-100), token utilization, estimated quality degradation, and recommendations for recovery. Call this periodically during long sessions or before critical decisions.

Retrieve health check history for an agent. Requires agent_id. Returns recent health checks and aggregate statistics.

Get service-wide utilization statistics: total calls, unique agents, model distribution, health score averages, and recent activity. Useful for operators monitoring service adoption and usage patterns.

概要

What is Context Rot Detection?

Context Rot Detection is an MCP service that gives AI agents real-time visibility into their own cognitive health. It measures performance degradation as the context window fills up, providing a health score (0–100) based on token utilization, retrieval accuracy, and session fatigue. It is designed for developers building long-running production agent systems.

How to use Context Rot Detection?

Install via npx (zero install) or npm global install. Configure as an MCP client tool for Claude Code or Claude Desktop, or run with Docker. Use the check_my_health tool periodically to analyze the current context window health, passing required token count and optional parameters.

Key features of Context Rot Detection

  • Health score (0–100) based on token utilization, retrieval accuracy, and session fatigue
  • Model-specific degradation curves for 15+ curated models (Claude, GPT, Gemini, o-series)
  • Auto-resolves any HuggingFace model, caching context window in SQLite
  • Lost-in-the-middle risk scoring based on Stanford research
  • Actionable recovery recommendations (compact context, offload, checkpoint)
  • Per-agent health history tracking and service-wide utilization statistics

Use cases of Context Rot Detection

  • Monitoring real-time cognitive health of long-running AI agents
  • Detecting context rot before critical decisions or actions
  • Analyzing per-agent health trends and service-wide degradation patterns
  • Providing actionable recommendations to mitigate quality loss

よくある質問

1

What signals make up the health score?

The health score is a weighted composite of token utilization quality (40%), retrieval accuracy (25%), tool-call burden (20%), and session length (15%).

2

How are model-specific degradation curves determined?

Curves are derived from empirical research (Chroma, Stanford, Redis) and are provided for 15+ curated models. Any HuggingFace model can be auto-resolved by fetching its config.json to extract context window size.

3

What data is stored and where?

Health history is stored in a SQLite database configured via the `HEALTH_HISTORY_DB` environment variable (defaults to `:memory:`). The server caches HuggingFace model lookups in the same database.

4

Does the server require network access?

Yes, for HuggingFace model auto-resolution it fetches `config.json` from the HuggingFace repo. If that fails, it falls back to conservative defaults. Local model detection does not require network.

5

What transports and authentication are supported?

The server uses stdio transport (standard MCP). There is no built-in authentication; it is intended to be invoked by MCP clients like Claude Desktop or Claude Code.

コメント

「その他」の他のコンテンツ

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.0K
P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

広告掲載