SkillAgentSearch skills...

agent-rack

MCP server that runs CLI AI coding agents (Claude Code, Codex, opencode, Antigravity) as sub-agents from any MCP client — background sessions, terminal dashboard, structured code review

Install / Use

claude mcp add lakpriya1s -- npx -y github:lakpriya1s/agent-rack

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

69/100

Supported Platforms

Claude Code
Claude Desktop
Cursor
OpenAI Codex

Our assessment of agent-rack

agent-rack scores 69/100 on our quality scale, 3921st of 4,705 Development & Engineering skills we index.

Its MCP Server is 60 KB long, well organised into 52 sections with 40 code examples: long enough that it reads more like full documentation than a focused instruction file, which agents can find harder to follow.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
21/30
Structure
20/20
Description
15/15
Adoption
3/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 90/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-11-16. Automated pattern scan on 2026-11-16. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

agent-rack compared with similar skills

All 4 of these similar skills score higher than agent-rack; compare them before choosing.

SkillScoreStarsUpdatedFormat
agent-rack (this skill)by lakpriya1s6933mo agoMCP Server
taste-skillby Leonxlnx100117.0k8d agoCLAUDE.md
Agent-Reachby Panniantong100112.4k9d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.9ktodayCLAUDE.md

Frequently asked questions

How do I install agent-rack?
Run claude mcp add lakpriya1s -- npx -y github:lakpriya1s/agent-rack. The install tabs above show the steps for each supported agent.
Which AI agents does agent-rack work with?
It is written for Claude Code, Claude Desktop, Cursor and OpenAI Codex, as a MCP Server file. Other agents that read the same format can often use it too.
Is agent-rack safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 90/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is agent-rack still maintained?
The repository was last updated about 3 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="./assets/agent-rack-wordmark-dark.svg"> <img src="./assets/agent-rack-wordmark-light.svg" alt="agent-rack — MCP server that exposes CLI AI coding agents as MCP tools" width="480"> </picture>

agent-rack — run CLI AI coding agents as MCP tools

Bridge any CLI coding agent into any MCP client<br> An MCP server for delegating work to Claude Code, Codex, opencode, and Antigravity sub-agents — from Claude Code, Claude Desktop, Cursor, VS Code, or any other MCP client.

npm License: MIT Node

</div>

agent-rack wraps command-line AI coding agents behind a single Model Context Protocol server. It ships with four agents built in — claude, codex, opencode, and Antigravity (agy) — but isn't limited to them: any other local CLI coding agent can be wired in with a small adapter (see Connecting your own CLI agent). Point any MCP client at it, and it spawns sub-agents synchronously for one-shot tasks, or as background sessions with log streaming, follow-up input, and cancellation.

It also ships a structured, adversarial-capable code review tool (agent_review) that runs read-only and returns validated JSON instead of free text, plus 9 packaged commands and 2 auto-activated guidance skills for Claude Code, Cursor, and Antigravity.


Contents

What it's for

The main thing agent-rack buys you is another agent's context, not just another tool call. A sub-agent reads files, runs commands, and reasons on its own budget, then hands back a result — so the work never lands in your main conversation's context window.

  • Parallel sub-agents. Fan several background sessions out at once (agent_session_create), poll them, and collect results — a test-fixing session, a docs session, and a refactor session running side by side.
  • Second-opinion code review. Have Codex review what Claude Code just wrote (or the reverse) via agent_review, and get validated JSON findings back instead of prose you have to re-read.
  • Model and vendor diversity. Your client stays whatever you like using; the sub-agent can be a different CLI, a different vendor, and a different model per call (see Changing models).
  • Long-running work off the critical path. Start a migration or a large test run as a background session, keep working, and check on it with agent_session_logs or the terminal dashboard.
  • One protocol for every CLI. Any local CLI coding agent — including one that isn't built in — becomes the same set of MCP tools everywhere (see Connecting your own CLI agent).

You keep using whichever CLIs you already pay for: agent-rack drives the binaries on your $PATH with your existing logins. It never asks for an API key and never calls a model itself.

Supported MCP clients and agents

Clients agent-rack can register itself with (see Install):

| MCP client | Command | Scope | | --- | --- | --- | | Claude Code | agent-rack install --target claude (or the plugin) | project or user | | Codex CLI | agent-rack install --target codex | user | | Claude Desktop | agent-rack install --target desktop | user (macOS path) | | Cursor | agent-rack install --target cursor | project or user | | Antigravity | agent-rack install --target antigravity | user | | OpenCode | agent-rack install --target opencode | user | | VS Code, GitHub Copilot, anything else | agent-rack snippet vscode → paste the JSON | — |

Agents it can spawn as sub-agents:

| Agent | Agent id | CLI | Transport | Follow-up input | | --- | --- | --- | --- | --- | | Claude Code | claude | claude | claude_stream_json | yes — resume | | Codex | codex | codex | codex_exec_json | yes — resume | | OpenCode | opencode | opencode | pty_interactive | yes — live | | Antigravity | agy | agy | agy_stream | no | | Your own CLI | anything | anything | pty_interactive or a custom adapter | depends |

See Follow-up input for what live and resume mean — they need the session to be in opposite states.

Install

Using Claude Code? Skip the steps below entirely and install the Claude Code plugin instead — it registers the MCP server automatically and adds slash commands (/agent-rack:run, /agent-rack:review, …) for every tool:

/plugin marketplace add lakpriya1s/agent-rack
/plugin install agent-rack@agent-rack
/reload-plugins

For every other MCP client, no cloning, no config file to write by hand — just register it. Not sure which targets apply to you? Run the interactive wizard instead — it detects what's actually installed (including project-local .claude/.cursor folders, offering project-vs-global registration for those two) and asks before registering with each:

npx agent-rack setup

Or register with a specific target directly:

npx agent-rack install --target claude       # Claude Code CLI
npx agent-rack install --target codex        # Codex CLI
npx agent-rack install --target desktop      # Claude Desktop
npx agent-rack install --target cursor       # Cursor
npx agent-rack install --target antigravity  # Antigravity
npx agent-rack install --target opencode     # OpenCode
npx agent-rack snippet vscode                # print a snippet to paste anywhere else

claude and cursor also accept --scope project to register only for the current project (a git-shareable .mcp.json/.cursor/mcp.json in the project root) instead of globally for every project — see install below for details.

Then restart your MCP client to pick up the new tools. That's it — with no config file present, agents are automatically scoped to whichever directory your MCP client launches the server from (almost always your project root). See Configuration below only if you need to customize that.

Prefer a global install so the agent-rack command is always on hand?

npm install -g agent-rack
agent-rack install --target claude

--target desktop writes to macOS's Claude Desktop config path (~/Library/Application Support/Claude/claude_desktop_config.json). On other platforms, run agent-rack snippet claude-desktop and paste the printed JSON into your config by hand.

Adding another client later

None of this is a one-time-only step. install --target <x> and setup are both safe to run again at any point after your first install — each target's registration is independent, so adding Cursor six months after you set up Claude Code doesn't touch Claude Code's registration at all, and re-running the same target is idempotent (it just confirms/repairs that one entry). There's nothing to migrate and no shared state between clients to keep in sync — every client still resolves the same agent-rack.config.json (see Configuration), it's only which clients know to spawn agent-rack that changes. Just restart the newly-registered client afterward to pick up the tools.

Requirements

  • Node.js 20+
  • Whichever underlying CLI(s) you intend to run must be on $PATH: claude, codex, opencode, and/or agy. Check with npx agent-rack agents.

MCP tools

Two execution models, pick based on how long the task runs and whether you need to watch it:

  • Synchronous — agent_run blocks until the sub-agent finishes and hands back its output directly. Simplest option for one-shot tasks.
  • Asynchronous — agent_session_* starts a sub-agent in the background and returns a sessionId immediately. Poll agent_session_status, stream agent_session_logs, or stop it early with agent_session_cancel. Use this for anything long-running or that you want to monitor mid-flight.

Follow-up input

agent_session_send continues a session's conversation. How it does that — and therefore what status the session must be in — depends on the agent's followUpMode:

| followUpMode | Agents | Send while the session is | Mechanism | | --- | --- | --- | --- | | live | opencode | running | Written straight to the still-running process. The only mode that can steer a turn mid-flight. | | resume | claude, codex | finished (completed) | The agent is restarted with its own resume flag (claude --resume <session_id>, codex exec resume <thread_id>), continuing the same conversation as a new turn. | | none | agy | — | No continuation; start a new session instead. |

For a resume agent, a completed session is not a dead end — it's the precondition. Sending puts the session back to status: "running" and increments turnCount; sending during a turn is refused, because a resume spawns a new process and two children must not run against one conversation. A cancelled session is refused as well: its conversation was interrupted mid-turn.

Continuity comes from the CLI's own session store, not from agent-rack — we pass the conversation id the CLI reported (session_id for claude, thread_id for codex) back to it. Antigravity is none because its --print output never reveals a per-run conversation id, and its --continue resumes "the most recent conversation" machine-wide, which would misroute a follow-up as soon as two sessions run at once.

live follow-up is not the same as interrupting. Only opencode can be sent input while it is working. Check followUpMode in agent_list_available or on the session info before telling a user they can steer a running turn.

Every configured agent also gets a shorthand tool — claude_run, codex_run, agy_run, opencode_run — identical to agent_run but with agent pre-filled.

agent_list_available

No parameters. Lists every configured agent and whether its binary is on $PATH.

[
  {
    "agentId": "claude",
    "name": "Claude Code CLI",
    "command": "claude",
    "transport": "claude_stream_json",
    "description": "Claude Code CLI streaming JSON agent",
    "status": "available",
    "capabilities": {
      "supportsFollowUp": true,
      "followUp": "resume",
      "supportsStreaming": true,
      "supportsNativeReadOnly": true,
      "promptTransport": "argv"
    },
    "executionPolicy": "workspace-write",
    "policyWarning": "Claude Code has no filesystem sandbox; 'workspace-write' is enforced by permission prompts and instructions only."
  },
  { "agentId": "codex", "..

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars3
CategoryDevelopment
Updated3mo ago
Forks1

Languages

TypeScript

Trust signals

90/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 low1 info