> For the complete documentation index, see [llms.txt](https://docs.bravostudio.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bravostudio.app/bravo-mcp/bravo-mcp.md).

# Bravo MCP

Bravo MCP turns AI assistants like Claude, ChatGPT and Cursor into a complete mobile-app pipeline — from a design source to a deployable React Native app.

Bravo MCP is a Model Context Protocol server that turns AI hosts ([Claude.ai](https://claude.ai), ChatGPT, Cursor, IDE plugins) into a complete mobile-app pipeline. You point it at a design source and it produces a deployable React Native (Expo + NativeWind) app — web, iOS, and Android from the same project.

## What it does

* **Design-driven app generation.** Figma is the primary source; Bravo projects work too. The design is the input, not a text prompt — fidelity tracks the design instead of drifting through prose.
* **Bravo Studio import.** Existing Bravo apps come in with API surface, UI-to-endpoint bindings, and auth config pre-wired — one-shot from your Bravo app ID.
* **Per-app backend.** Every project gets its own Convex deployment with a typed client, data tables, queries, and actions. Agents author backend code via the same write → finalize → approve loop they use for screens.
* **Recipe system for production concerns.** Drop-in modules for auth (Convex auth, external OAuth, external backends like Xano), custom fonts, webview integration, and more — each handles its own scaffolding, secrets, and runtime wiring.
* **Deploy pipeline.** Push to Cloudflare Pages (web) in \~3 minutes; ship Android `.apk` via EAS preview builds; promote to App Store / Play Store via your own Expo account.
* **Per-screen iteration loop.** Edit any screen any time. Submit-time validators catch the common deploy-breakers before they reach CI (font references, route targets, recipe-config mismatches, unwired API bindings).

## How it fits

* **The agent loop is yours.** Bravo MCP is the toolset; you choose the model (Claude, GPT, etc.) and the host ([Claude.ai](https://claude.ai), ChatGPT, Cursor, IDE plugins). The MCP server is hosted by Bravo; everything you build lives in your own GitHub repo + Convex deployment.
* **Plans.** Visitor (no Bravo account) gets a 1-app trial; Starter / Solo / Team / Business plans unlock higher caps and EAS native builds. Production native builds always run on your own Expo account regardless of plan.
* **Source of truth: the Bravo Studio dashboard.** If you've already built an app in Bravo, re-imports re-sync the canonical config — endpoints, auth, bindings, recipes. Your Bravo MCP screen code is untouched; only the platform integration layer regenerates.

## Get started

{% content-ref url="/pages/XXgdFCEx4HaEyxyNS248" %}
[Setup and usage guide](https://docs.bravostudio.app/bravo-mcp/bravo-mcp/setup-and-usage-guide.md)
{% endcontent-ref %}

{% content-ref url="/pages/dlWIPFMarxrvEfdH5UzI" %}
[How you can use Bravo MCP](https://docs.bravostudio.app/bravo-mcp/bravo-mcp/how-you-can-use-bravo-mcp.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.bravostudio.app/bravo-mcp/bravo-mcp.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
