MCP.so
Sign In

Claude Octopus

@xiaolai

Repository

About Claude Octopus

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

Basic information

Category

AI & Agents

Transports

stdio

Publisher

xiaolai

Submitted by

xiaolai

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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.

Comments

More AI & Agents MCP servers

MCP-LLM Bridge

patruff

Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools

976

MCP Manager for Claude Desktop

zueai

simple web ui to manage mcp (model context protocol) servers in the claude app

290

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739

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 for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K