$git clone https://github.com/Arenukvern/mcp_flutter_Inspect and drive a running Flutter app from your AI assistant._
| 1 | <div align="center"> |
| 2 | |
| 3 | # flutter-mcp-toolkit |
| 4 | |
| 5 | _Inspect and drive a running Flutter app from your AI assistant._ |
| 6 | |
| 7 | [](https://skills.sh/arenukvern/mcp_flutter) |
| 8 | [](https://pub.dev/packages/mcp_toolkit) |
| 9 | [](https://github.com/Arenukvern/mcp_flutter/actions/workflows/contract_gates.yml) |
| 10 | [](https://github.com/Arenukvern/mcp_flutter/actions/workflows/intentcall_eval.yml) |
| 11 | [](https://github.com/Arenukvern/mcp_flutter/actions/workflows/skill_assets_drift.yml) |
| 12 | [](https://docs.page/arenukvern/mcp_flutter/) |
| 13 | [](https://opensource.org/licenses/MIT) |
| 14 | [](https://flutter.dev) |
| 15 | [](https://smithery.ai/server/@Arenukvern/mcp_flutter) |
| 16 | [](https://github.com/Arenukvern/mcp_flutter#contributors-) |
| 17 | <a title="Discord" href="https://discord.com/invite/y54DpJwmAn" ><img src="https://img.shields.io/discord/696688204476055592.svg" /></a> |
| 18 | [](https://github.com/Arenukvern/skill_steward) |
| 19 | |
| 20 | </div> |
| 21 | |
| 22 | - 📖 **Docs:** [docs.page/arenukvern/mcp_flutter](https://docs.page/arenukvern/mcp_flutter/) |
| 23 | - 🤝 **Contribute:** [guide](docs/contributing/contribution_guide.mdx) · [contributors](docs/contributing/contributors.mdx) · [code of conduct](CODE_OF_CONDUCT.md) · [security](SECURITY.md) |
| 24 | |
| 25 | `flutter-mcp-toolkit` is a Dart MCP server + Flutter package that lets AI Agents (Codex, Zed, Cursor, Intent, Claude Code, Cline, etc..) take (semantic snapshots, tap widgets, type into forms, hot-reload, and read logs from a Flutter app) or create __its own tools and resources at runtime__ using MCP Toolkit — without leaving the conversation and work with Flutter apps in closed feedback loop - see example of it described in [OpenAI Agentic Harness](https://openai.com/index/harness-engineering/). |
| 26 | |
| 27 |  |
| 28 | |
| 29 | The picture's story: the toolkit gives an AI assistant a shared window and control loop into a running Flutter app, so it can inspect state, act like a user, hot reload, read proof, and use custom tools from your app instead of guessing. |
| 30 | |
| 31 |  |
| 32 | |
| 33 | > ![NOTICE]: Version 4 is currently a prerelease train. Use `4.0.0-dev.5` only if you are intentionally testing the new architecture; otherwise stay on the latest stable 3.x release until `4.0.0` is promoted. |
| 34 | |
| 35 | ## Get started in 4 steps |
| 36 | |
| 37 | ```bash |
| 38 | # 1. Install the binary |
| 39 | curl -fsSL https://raw.githubusercontent.com/Arenukvern/mcp_flutter/main/install.sh | bash |
| 40 | # Installs flutter-mcp-toolkit plus the short fmtk alias for repeated CLI loops. |
| 41 | |
| 42 | # 2. Add the toolkit to your Flutter app |
| 43 | cd my-flutter-app |
| 44 | flutter-mcp-toolkit codegen-init # adds mcp_toolkit + emits main.dart snippet |
| 45 | |
| 46 | # 3. Install skills for your AI agent |
| 47 | flutter-mcp-toolkit init claude-code # or: cursor | codex | cline | agents-skills | all |
| 48 | # Alternative (skills only): npx skills add Arenukvern/mcp_flutter -a |