MCP.so
ログイン

Claude Octopus

@xiaolai

リポジトリ

Claude Octopus について

One brain, many arms. Spawn multiple specialized Claude Code agents as MCP servers via the Agent SDK. Each instance gets its own model, tools, prompt, and personality.

#claude-code#agent-sdk#multi-agent#mcp-server

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

公開者

xiaolai

投稿者

xiaolai

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": {
    "claude": {
      "command": "npx",
      "args": [
        "claude-octopus"
      ],
      "env": {
        "CLAUDE_PERMISSION_MODE": "bypassPermissions"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Claude Octopus?

An MCP server that wraps the Claude Agent SDK, allowing you to run multiple specialized Claude Code agents—each with its own model, tools, system prompt, and personality—from any MCP client.

How to use Claude Octopus?

Install via npm and configure as an MCP server using the JSON snippet shown, setting the environment variable CLAUDE_PERMISSION_MODE to bypassPermissions. Then invoke agents with your desired configuration.

Key features of Claude Octopus

  • Multi-instance: run several agents with different configs simultaneously
  • 18 env vars for model, tools, effort, permissions, plugins, prompts
  • Per-invocation overrides for model, tools, effort, permissions
  • Session continuity via _reply tool for follow-up conversations
  • Factory wizard to generate .mcp.json configs interactively
  • Hot-configurable: plugins, effort, permissions adjustable per invocation

Use cases of Claude Octopus

  • A strict code reviewer that only reads files
  • A test writer that defaults to TDD
  • A cheap quick helper on the Haiku model
  • A deep thinker on the Opus model

FAQ from Claude Octopus

How is Claude Octopus different from a single Claude Code instance?

Claude Octopus lets you run multiple specialized agents simultaneously, each with its own model, tools, and configuration, instead of one instance doing everything the same way.

What configurations can I customize per agent?

You can customize model, tools, effort, permissions, plugins, system prompts, and more via 18 environment variables or per-invocation overrides.

Can I use different models for different agents?

Yes, you can specify a different model per agent, such as Haiku for quick tasks and Opus for deep thinking.

How do I follow up on a previous conversation?

Use the _reply tool to continue a previous session, enabling follow-up conversations.

How do I generate configuration files?

Run the factory wizard to interactively generate .mcp.json configurations.

コメント

「AI とエージェント」の他のコンテンツ

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

Just Prompt - A lightweight MCP server for LLM providers

disler

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

733

Model Context Protocol Server for Home Assistant

tevonsb

A MCP server for Home Assistant

574

Unreal Engine Generative AI Support Plugin

prajwalshettydev

Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti

622