agentmods.dev

claude-octopus

claude-octopus is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from xiaolai/claude-octopus. Its token cost is not measured, scanned A, original, ISC.

An MCP server that starts multiple independently configured Claude Code agents. Claude Code is a coding assistant that can run from the command line.

In plain words
What is it for?
Use it to launch multiple Claude Code agents and configure their models, tools, prompts, and permission modes.
Why use it?
It provides a way to run several specialized agents with separate settings and permissions.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 21repo today A scan tokens not measured original ISC

Good fit Use it to launch multiple Claude Code agents and configure their models, tools, prompts, and permission modes.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/xiaolai/claude-octopus/claude-octopus
View source ↗ xiaolai/claude-octopus
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/xiaolai/claude-octopus

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-octopus

README.md
[![agentmods](https://agentmods.dev/badge/mcp/xiaolai/claude-octopus/claude-octopus/github.svg)](https://agentmods.dev/mcp/xiaolai/claude-octopus/claude-octopus)
Your own site
<a href="https://agentmods.dev/mcp/xiaolai/claude-octopus/claude-octopus"><img src="https://agentmods.dev/badge/mcp/xiaolai/claude-octopus/claude-octopus/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-octopus

Your own site · 80×15
<a href="https://agentmods.dev/mcp/xiaolai/claude-octopus/claude-octopus"><img src="https://agentmods.dev/badge/mcp/xiaolai/claude-octopus/claude-octopus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-octopus scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 18 lines

What it actually says

{
  "claude-octopus": {
    "command": "npx",
    "args": [
      "-y",
      "claude-octopus"
    ],
    "env": {
      "ANTHROPIC_API_KEY": "",
      "CLAUDE_TOOL_NAME": "",
      "CLAUDE_MODEL": "",
      "CLAUDE_PERMISSION_MODE": "",
      "CLAUDE_ALLOWED_TOOLS": "",
      "CLAUDE_APPEND_PROMPT": "",
      "CLAUDE_FACTORY_ONLY": ""
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 18 lines scan A c531eeb75b36

Subscribe to this mod's changes

claude-octopus is an MCP server published in the GitHub repository xiaolai/claude-octopus (21 stars, last pushed today), licensed ISC. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsClaude Codeagent-sdkclaude-agent-sdkmcpmcp-servermodel-context-protocol
Related

Other mcp servers, from other repositories

hypermnesia-mcp

Scientifically-grounded memory system based on computational neuroscience research. Runs locally from the hypermnesia-mcp Python package.

cdeust/Cortex · not measured

ActiveDirectoryMCP

MCP server "ActiveDirectoryMCP" as configured in alpadalar/ActiveDirectoryMCP. Launched with uv --directory /absolute/path/to/ActiveDirectoryMCP run activedirectory-mcp. Needs 3 environment variables to run.

alpadalar/ActiveDirectoryMCP · not measured

behavior-mcp

MCP server "behavior-mcp" as configured in putervision/state-memory-mcp. Launched with behavior-mcp run. Needs 1 environment variable to run.

putervision/state-memory-mcp · not measured

plonk

Plonk gives agents local macOS tools for windows, workspaces, screenshots, OCR, and more. Runs locally from the plonk-mcp npm package.

ostapondo/Plonk · not measured

mcp-pve

Manage Proxmox VE through AI assistants. Runs locally from the @samik081/mcp-pve npm package. Needs 3 environment variables to run.

Samik081/mcp-pve · not measured

umami

MCP server for Umami Analytics API v2 — websites, stats, events, reports, and realtime. Runs locally from the @mikusnuz/umami-mcp npm package. Needs 4 environment variables to run.

mikusnuz/umami-mcp · not measured