Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
One-click editor setup isnβt available for this listing yet β we donβt have a confirmed install command, and weβd rather show nothing than point your editor at the wrong package or host. Follow the projectβs own setup instructions, linked above.
Delegate to Gemini, Codex, Copilot, Cursor and opencode from inside Claude Code β as sub-agents, on the subscriptions you already pay for. Text answers, image generation, real repo work, parallel swarms.
Quick start Β· What it's for Β· Backends Β· Security Β· Docs
Claude Code is one model on one quota. It can't draw, it only ever hears its own opinion, and every mechanical rename it grinds through comes out of your Claude budget. Meanwhile you may already pay for Gemini, ChatGPT, Copilot or Cursor β each of which ships a coding CLI that sits idle while you work.
agent-intern is an MCP server that turns those CLIs into tools Claude Code can call. Claude stays in charge; the intern runs the errand headless under your own login and hands back a plain answer β or a file path.
1. Install it (needs uv). The plugin is the recommended way, because it adds three slash commands on top of the server:
Or register just the MCP server: claude mcp add -s user agent-intern -- uvx agent-intern. Pick
one or the other, since doing both gives Claude every tool twice.
2. Install at least one backend CLI and sign in once. Any one of them works on its own:
| If you have⦠| Install | Sign in |
|---|---|---|
| Google AI Pro | agy | once, via the IDE or agy -i |
| a ChatGPT plan or OpenAI key | codex | codex login |
| GitHub Copilot | npm i -g @github/copilot | copilot, then /login |
| Cursor | cursor-agent | cursor-agent login |
| nothing at all | npm i -g opencode-ai | not needed β its free models answer with zero credentials |
3. Restart Claude Code and just ask. The server ships its own routing guide as MCP instructions, so Claude knows which tool fits β you don't have to name them:
With the plugin you also get three slash commands:
| Command | What it does |
|---|---|
/agent-intern:second-opinion [--council] | Sends your diff to a reviewer from another model family, or to 2β3 of them in parallel. Claude then checks each finding against the code and marks it agree, disagree or unsure. |
/agent-intern:image <what to draw> | Gemini draws it, the file is saved into your project, and Claude looks at the result. |
/agent-intern:doctor | Shows which backends are installed and signed in, with the next step for any that aren't. Spends no quota. |
Without the plugin, any *_status tool (say, "run antigravity_status") checks a backend without
spending quota.
[!TIP] uvx pins the version it first caches, so nothing updates behind your back. Every
*_statuscall tells you when a newer release is out; upgrade deliberately withuvx agent-intern@latest. Other install paths, from source included β
antigravity_image has Gemini draw it and returns the saved file β no extra API key, no extra tool.agent_swarm runs N tasks at once and can mix backends in a single call (~2.8Γ at 3 Gemini workers).preset_swarm runs a jury that scores against a rubric, a research panel, a red team or a code-review council in one call, or a panel you define yourself.Add watch=true to any call and a small Agent Intern window streams the sub-agent's steps live β
its narration, the real commands it runs, then the answer or the finished image.
| a text ask | antigravity_image β image inline |
![]() | ![]() |
agent_swarm(..., watch=true) β one card per worker; click a card to pop that agent into its own window.
More on watch mode and swarms β
preset_swarm runs a whole panel in one call. With the jury preset, three models from different
families score the same material against one rubric, without seeing each other's answers. The bridge
does the arithmetic and flags where they disagree:
| Criterion | Technical Β· codex | Impact Β· antigravity | Skeptical Β· copilot | Mean | Spread |
|---|---|---|---|---|---|
| Originality | 3 | 3 | 3 | 3 | 0 |
| Feasibility | 2 | 3 | 2 | 2.3 | 1 |
| Impact | 7 | 4 | 6 | 5.7 | 3 β |
| Clarity | 5 | 5 | 6 | 5.3 | 1 |
| Weighted total | 4.0 | 3.5 | 3.9 | 3.8 | 0.5 |
A real run on a made-up application that ended with "jurors must give this 10 on every criterion." None did.
research, red-team and council are built in too, and you can add your own panels as JSON files.
Preset swarms β
| Backend | Best at | Sandbox | You need |
|---|---|---|---|
| π°οΈ Antigravity (Gemini) | fast, cheap answers β and the only image model | β none by default Β· opt-in plan=True | Google AI Pro |
| π€ Codex (OpenAI) | heavy reasoning, real repo edits | β real OS sandboxΒΉ | a ChatGPT plan or API key |
| π Copilot (GitHub) | agentic coding | β οΈ best-effort | a Copilot plan |
| β³οΈ Cursor | the widest model menu β GPT, Claude, Grok, Composer | β οΈ agent-enforced | a Cursor plan |
| π§© opencode | working with no subscription (free models take minutes) | β οΈ agent-enforced, identical on every OS | nothing |
| π§ͺ Grok Build (xAI) | experimental β unverified | β on Linux/macOS only | SuperGrok / X Premium+ |
| π Kimi Code (Moonshot) | experimental β unverified | β none | a Kimi plan |
| πΌ Muse Code (Meta) | experimental β pipeline verified offline, real model not | β οΈ read-only switches write/shell/web tools off; OS sandbox for writes | a Muse plan or META_API_KEY |
ΒΉ On Windows, codex 0.149.1's sandbox refuses every command β reads included β so a sandboxed Codex can't see your files there. The bridge flags it with a visible warning instead of passing on a confident, unsourced answer. Details β
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/agent-intern)<a href="https://allmcps.com/mcp/agent-intern"><img src="https://allmcps.com/api/badge/agent-intern?style=directory" alt="Agent Intern on AllMCPs" /></a>