Install it.
Put it to work.

Claude

In Claude Code, connect the local server:

1. Restart or reconnect your Claude session and check that the MCP tools are available.
2. Ask the agent to list the connected tools, search only the relevant local references, and review a small Swift file first. For changes, ask it to build and test, show the command results, and explain unresolved failures.

Claude Desktop: use the Desktop JSON setup instead of the CLI command. Preserve existing settings.

Build a whole app from one sentence: the /ios-build agent is in ios-agent-mcp 2.10.0, now published on npm. After connecting the server above, install the Claude Code command:

Then run /ios-build "<your app>". Needs a Mac with Xcode 16 or later. What the agent does and what has been verified.

Codex

Connect the server to your local Codex coding environment:

1. Open your app folder in Codex and reconnect the MCP server if needed.
2. Ask the agent to list the connected tools, search only the relevant local references, and review a small Swift file first. For changes, ask it to build and test, show the command results, and explain unresolved failures.

Use the local coding environment for source edits and Xcode workflows. The ChatGPT web setup below is different.

ChatGPT

ChatGPT web cannot run the local npx command on your Mac directly.

1. For guidance, use the skills-only release package through a supported import or plugin-development flow available to your account.
2. For connected tools, configure an HTTPS knowledge MCP endpoint or a supported private MCP tunnel. This project does not operate a public endpoint for you.
3. Follow the official connection guide (new tab). Account and workspace policy may limit access.
4. Ask for a scoped implementation plan and relevant Apple references. Use an appropriately connected local coding environment for builds, simulator execution and evidence.

The hosted knowledge server serves references and plans. It is not a remotely hosted Mac or simulator.

Gemini CLI

Connect the published server from your project folder:

1. Restart Gemini CLI and confirm the server is connected.
2. Ask the agent to list the connected tools, search only the relevant local references, and review a small Swift file first. For changes, ask it to build and test, show the command results, and explain unresolved failures.

This is for Gemini CLI, not Gemini web chat. The repository extension is an alternative for bundled guidance; check its version pin is published before installing it. Use one setup method to avoid duplicate tools.

Grok Build

Connect the existing server to the official Grok coding CLI:

grok mcp doctor ios-agent --json

Install Grok through its official instructions. Node.js 20+ is required; local native builds and simulator operations need macOS and Xcode. Grok account access is separate.

Verified October 28: Grok Build 1.0.70 connected to ios-agent-mcp 2.10.3 and discovered 82 tools. No model-driven session or tool execution is claimed by this connectivity check.

Check grok inspect for imported Claude/Cursor connections before adding a duplicate. Grok web chat and the remote xAI API are separate environments; this setup does not deploy a public MCP endpoint or install a slash command.

AI/ML API (optional companion)

Run the AI/ML API hosted model gateway beside the local iOS Agent server, on your own AI/ML API account, for icon and asset concepts. In Claude Code:

Then run /mcp, select aimlapi and choose Authenticate. Sign-in is OAuth in your browser; inference is billed to your AI/ML API balance. Do not put an API key in your app repository.

iOS Agent MCP never calls this service and is not bundled with it. Generate a concept there, then turn it into a layered icon or asset catalog with the local tools. Not verified from this project; the steps follow the provider’s published setup.

Muse Code

Install the server outside the agent sandbox:

Merge this into ~/.config/muse/settings.json. Keep your other settings and existing servers.

{
  "schema_version": 1,
  "mcpServers": {
    "ios-agent": { "command": "ios-agent-mcp", "args": [] }
  }
}

1. Restart Muse. If the executable is not found, use its absolute path from command -v ios-agent-mcp.
2. Ask the agent to list the connected tools, search only the relevant local references, and review a small Swift file first. For changes, ask it to build and test, show the command results, and explain unresolved failures.

Muse tool discovery and a Stop hook have been verified; a complete model-driven app-building session has not.

Start small. Verify the result.

Try this prompt after your local MCP connection is working:

Review this app’s Swift concurrency. Search only the relevant local references.
Explain each finding with its file and line, and separate heuristics from confirmed bugs.
Propose the smallest fix. After approval, implement it, run the relevant tests,
and report what passed and what remains unverified.

When a step fails, ask the agent to show the relevant diagnostic, explain its next fix and report the result of verification. Keep this feedback in the development session, not in the app’s interface. Public issue reporting is separate: prepare a local preview, then review and authorize submission. A private chat-based option is being prepared in source; it is not deployed or available in npm 2.7.0.

For a new app, describe screens, persistence and acceptance criteria first. A starter is scaffolding; your agent still implements the features. Prefer one feature and one verification loop at a time.

Do not assume a connected tool means the app is complete. Ask for actual build/test results and simulator evidence where applicable.