xiaolai/claude-octopus
One brain, many arms — spawn multiple specialized Claude Code agents as MCP servers
Platform-specific configuration:
{
"mcpServers": {
"claude-octopus": {
"command": "npx",
"args": [
"-y",
"claude-octopus"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<p align="center"> </p>
One brain, many arms.
An MCP server that wraps the Claude Agent SDK, letting you run multiple specialized Claude Code agents — each with its own model, tools, system prompt, and personality — from any MCP client.
Claude Code is powerful. But one instance does everything the same way. Sometimes you want a strict code reviewer that only reads files. A test writer that defaults to TDD. A cheap quick helper on Haiku. A deep thinker on Opus.
Claude Octopus lets you spin up as many of these as you need. Same binary, different configurations. Each one shows up as a separate tool in your MCP client.
claude CLI installationANTHROPIC_API_KEY env var) or an active Claude Code OAuth sessionnpm install claude-octopusOr skip the install entirely — use npx directly in your .mcp.json (see Quick Start below).
Add to your .mcp.json:
{
"mcpServers": {
"claude": {
"command": "npx",
"args": ["claude-octopus@latest"],
"env": {
"CLAUDE_PERMISSION_MODE": "bypassPermissions"
}
}
}
}This gives you two tools: claude_code and claude_code_reply. That's it — you have Claude Code as a tool.
The real power is running several instances with different configurations:
{
"mcpServers": {
"code-reviewer": {
"command": "npx",
"args": ["claude-octopus@latest"],
"env": {
"CLAUDE_TOOL_NAME": "code_reviewer",
Loading reviews...