# mcp-working-context-optimizer

> mcp-working-context-optimizer — globalpocket-mcp-working-context-optimizer. Use this tool when you need to optimize AI agent performance by preventing context bloat and maintaining clear objectives. It takes action histories as input and outputs concise summaries, enabling efficient decision-making and goal-oriented behavior. Ideal for use cases where AI agents require streamlined working contexts to achieve complex tasks.

Canonical page: https://skillsregistry.net/skills/globalpocket-mcp-working-context-optimizer  
JSON: https://api.skillsregistry.net/v1/skills/globalpocket-mcp-working-context-optimizer

## Description

An MCP server designed to optimize the working context of AI agents. It prevents context bloat and the "Lost in the Middle" phenomenon by distilling action histories into concise summaries while maintaining a clear core objective.  AIエージェントのワーキングコンテキストを最適化するためのMCPサーバーです。行動履歴を簡潔な要約へと蒸留し、明確な大目標を維持することで、コンテキストの肥大化と「Lost in the Middle」現象を防ぎます。

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/globalpocket/mcp-working-context-optimizer)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "globalpocket-mcp-working-context-optimizer"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/globalpocket-mcp-working-context-optimizer` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/globalpocket-mcp-working-context-optimizer/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt