Flutter MCP Toolkit MCP Server
io.github.Arenukvern/flutter-mcp-toolkit
Inspect and drive Flutter debug apps with AI: semantic snapshots, widget interaction, and custom runtime tools.
What is the Flutter MCP Toolkit MCP server?
The Flutter MCP Toolkit is a Dart MCP server and Flutter package that enables AI agents to inspect running Flutter apps, take semantic snapshots, interact with widgets, and access custom tools registered at runtime. It creates a closed feedback loop between an AI assistant and a Flutter application, allowing agents to inspect state, act like a user, hot-reload, and verify changes without leaving the conversation.
Flutter MCP Toolkit bridges AI agents (Claude, Cursor, Codex, Cline) with running Flutter apps. It exposes 30 MCP tools across inspection, interaction, debug, and lifecycle categories—semantic snapshots, widget tapping, form filling, hot-reload, log reading, and Dart expression evaluation. Apps can also register custom MCP tools dynamically at runtime, enabling domain-specific agent capabilities tailored to your app.
How to install Flutter MCP Toolkit
Copy-paste configuration for popular MCP clients.
Tools & capabilities
Tools this server exposes to the agent.
fmt_semantic_snapshot— Capture semantic snapshot of the running Flutter app UIfmt_screenshot— Take a screenshot of the running appfmt_tap— Tap a widget by identifier or coordinatesfmt_scroll— Scroll within a scrollable widgetfmt_type— Type text into a focused input fieldfmt_fill_form— Fill form fields with provided valuesfmt_hot_reload— Trigger hot-reload of the Flutter appfmt_hot_restart— Trigger hot-restart of the Flutter appfmt_navigate— Navigate to a named routefmt_wait_for— Wait for a condition to be metfmt_view_details— Get detailed information about a widgetfmt_errors— Retrieve recent errors from the appfmt_logs— Read recent debug logsfmt_vm_info— Get Dart VM informationfmt_evaluate_dart— Evaluate Dart expressions in the running appfmt_discover_apps— Discover running Flutter debug apps
Use cases
- Automate Flutter app testing by having an AI agent inspect UI, tap buttons, fill forms, and verify results in real-time
- Debug Flutter apps interactively: take snapshots, read logs, evaluate Dart expressions, and hot-reload while the agent observes changes
- Build custom AI-driven workflows by registering domain-specific MCP tools in your Flutter app that agents can call at runtime
- Develop Flutter features with AI assistance: agent inspects the app, suggests changes, hot-reloads, and verifies the implementation
- Create closed-loop agent-app feedback systems where AI can see proof of changes and adapt its next action based on actual app state
Flutter MCP Toolkit MCP server FAQ
It's a Dart MCP server and Flutter package that lets AI agents inspect and control running Flutter debug apps. Agents can take semantic snapshots, tap widgets, type text, hot-reload, read logs, and call custom tools you register in your app—all in real-time.
Yes, Flutter MCP Toolkit is open-source under the MIT license.
Run `flutter-mcp-toolkit init cursor` or `flutter-mcp-toolkit init claude-code` to auto-configure your agent. Alternatively, manually add the OCI image `ghcr.io/arenukvern/flutter-mcp-toolkit:4.0.0` to your MCP server config, or use `npx skills add Arenukvern/mcp_flutter`.
Yes, you must add the `mcp_toolkit` package to your Flutter app and call the bootstrap code. Run `flutter-mcp-toolkit codegen-init` in your app directory to auto-generate the required setup.
None. The toolkit communicates with your local Flutter debug app over a local connection. No external services or API keys are needed.
Yes. Apps can register custom MCP tools and resources at runtime via the `mcp_toolkit` package, allowing agents to call domain-specific functionality without leaving the conversation.
README (reference)
Source of truth, from the repository.
flutter-mcp-toolkit
Inspect and drive a running Flutter app from your AI assistant.
<a title="Discord" href="https://discord.com/invite/y54DpJwmAn" ><img src="https://img.shields.io/discord/696688204476055592.svg" /></a>
- 📖 Docs: docs.page/arenukvern/mcp_flutter
- 🤝 Contribute: guide · contributors · code of conduct · security
flutter-mcp-toolkit is a Dart MCP server + Flutter package for AI agents (Codex, Zed, Cursor, Intent, Claude Code, Cline, and more). Agents can inspect a running Flutter app, take semantic snapshots, tap widgets, type into forms, hot-reload, and read logs. Apps can also register their own MCP tools and resources at runtime via MCP Toolkit — all without leaving the conversation. The result is a closed feedback loop between agent and app; see OpenAI Agentic Harness for an example of this pattern.

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.

![NOTICE]: Version 4 is now stable. Earlier
4.0.0-dev.*builds were prerelease testing builds of the new architecture.
Get started in 4 steps
# 1. Install the binary
curl -fsSL https://raw.githubusercontent.com/Arenukvern/mcp_flutter/main/install.sh | bash
# Installs flutter-mcp-toolkit plus the short fmtk alias for repeated CLI loops.
# 2. Add the toolkit to your Flutter app
cd my-flutter-app
flutter-mcp-toolkit codegen-init # adds mcp_toolkit + emits main.dart snippet
# 3. Install skills for your AI agent
flutter-mcp-toolkit init claude-code # or: cursor | codex | cline | agents-skills | all
# Alternative (skills only): npx skills add Arenukvern/mcp_flutter -a cursor -y
# 4. Run
flutter run --debug
That's it. Your AI agent can now inspect and drive the running app — and your app can expose custom MCP tools at runtime (see Dynamic Tools Registration below).
📰 News
-
2026-07-11 - v4 new Live Demos records: v4 semantic snapshot etc.. with Grok Build CLI, v4 with IntentCall power - WebMCP projection
-
2026-05-26 — v3.1.0: Platform-view capture routing, macOS/iOS Simulator host screenshots, web CDP tab capture (SCK → CDP → flutter_layer), and cross-platform showcase platform views.
Install from marketplaces
| Platform | Command / link |
|---|---|
| Any agent (recommended) | flutter-mcp-toolkit init <agent> — see AI agent setup |
| Claude Code (git catalog) | /plugin marketplace add Arenukvern/mcp_flutter then install flutter-mcp-toolkit |
| Codex (git catalog) | codex plugin marketplace add Arenukvern/mcp_flutter |
| Cursor (local plugin) | flutter-mcp-toolkit init cursor |
| Skills only | npx skills add Arenukvern/mcp_flutter -a <agent> -y (add MCP via init or manual JSON) |
| MCP registries | Official MCP Registry — server io.github.Arenukvern/flutter-mcp-toolkit (OCI image: ghcr.io/arenukvern/flutter-mcp-toolkit), Smithery, MseeP |
Docker / MCP Registry install
The official registry serves an OCI image from GHCR. Point any MCP client at it:
{
"mcpServers": {
"flutter-mcp-toolkit": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--network=host",
"ghcr.io/arenukvern/flutter-mcp-toolkit:4.0.0"
]
}
}
}
See Docker guide for flags, version pinning, and networking notes.
Maintainers submitting to official stores: marketplace submission runbook. Full matrix: marketplace distribution.
Documentation
- Docs for AI Agent and Human - wiki + llms.txt
- Migrating v2 → v3 —
fmt_*MCP tools, binaries, client config keys,validate-runtime. - MCPCallEntry to AgentCallEntry migration —
MCPCallEntryremoval,AgentCallEntry, platformcodegen sync,fmt_migrate_agent_entries. - IntentCall consumer guide — hosted
intentcall_*dependency policy, consumer proof gates, and the boundary betweenmcp_flutterand upstream IntentCall architecture. - Why this repo matters — what it is, why it exists.
- CLI vs MCP — pick the right mode.
- Feature map — the 30 tools.
- AI agent setup - for AI Agents.
- Marketplace distribution — Claude, Cursor, Codex, skills.sh.
- Architecture — for contributors.
- Quick Start, Configuration, MCP RPC description
Published packages
The server binary lives in mcp_server_dart and is shipped through GitHub
Release artifacts as flutter-mcp-toolkit, fmtk, and
flutter-mcp-toolkit-server; it is not a pub.dev package.
Development support
| Need | Start here |
|---|---|
| Contribute code or docs | CONTRIBUTING.md · Contribution guide |
| Add or credit contributors | Contributors guide · .all-contributorsrc |
| Report vulnerabilities | SECURITY.md |
| Validate local changes | steward probe --json --profile quick · make check-contracts |
| Maintain releases | Release train notes · flutter-mcp-toolkit-repo-maintainer |
| Install or update agent skills | AI agent setup · Marketplace distribution |
What it does
The default toolkit surface exposes 30 MCP tools under the fmt_* capability prefix across four categories:
- Inspection — semantic snapshot, view details, errors, screenshots, VM info
- Interaction — tap, scroll, type, fill forms, hot-reload, navigate, wait_for
- Debug — recent logs, evaluate Dart expressions
- Lifecycle — discover apps, hot-reload, hot-restart
See the flutter-mcp-toolkit-{guide,inspect,control,debug} skills for the full
reference (installed by flutter-mcp-toolkit init or npx skills add Arenukvern/mcp_flutter).
Install options: AI agent setup.
Dynamic Tools Registration
Flutter apps can register custom tools and resources at runtime. See how it
works in this short YouTube video.
The same arguments.connection targeting is supported by the CLI's exec,
batch, daemon command/execute, daemon watch/start, and snapshot step args.
[!NOTE] There is official MCP Server for Flutter from Flutter team which exposes Dart tooling. The main goal of this project is to bring power of MCP server tools by creating them in Flutter app, using dynamic MCP tools registration and close feedback loop for AI Agent. See how it works in short YouTube video. See Quick Start for more details. See original motivation behind the idea.
⚠️ Note on Dump RPCs
Dump RPC methods (like dump_render_tree) can produce huge token output and
are disabled by default. Enable with --dumps. See
mcp_server_dart README for the full flag surface.
🔒 Security
Generally, since you use MCP server to connect to Flutter app in Debug Mode, it should be safe to use. However, I still recommend to review how it works in ARCHITECTURE.md, how it can be modified to improve security if needed.
This MCP server is verified by MseeP.ai.
🔧 Troubleshooting
-
Connection Issues
- Ensure your Flutter app is running in debug mode
- Verify the port matches in both Flutter app and MCP server
- Check if the port is not being used by another process
- Safest explicit targeting: use
arguments.connection.uriand paste exact Flutter machineapp.debugPort.wsUri - If response includes
connection_selection_required, retry witharguments.connection.targetIdusing one URI fromavailableTargets(or setarguments.connection.uridirectly)
-
AI Tool Not Detecting Inspector
- Restart the AI tool after configuration changes
- Verify the configuration JSON syntax
- Check the tool's logs for connection errors
-
Dynamic Tools Not Appearing
- Ensure
mcp_toolkitpackage is properly initialized in your Flutter app - Check that tools are registered using
MCPToolkitBinding.instance.addEntries() - Use
fmt_list_client_tools_and_resourcesto verify registration - Hot reload your Flutter app after adding new tools
- Ensure
The Flutter MCP Server is registered with Smithery's registry, making it discoverable and usable by other AI tools through a standardized interface.
Integration Architecture
┌─────────────────┐ ┌───────────────────────┐ ┌─────────────────┐
│ │ │ Flutter App with │ │ │
│ Flutter App │<--->│ mcp_toolkit │<--->│ flutter-mcp- │
│ (Debug Mode) │ │ (VM Svc. Extensions │ │ toolkit-server │
│ │ │ + Dynamic Tools) │ │ │
└─────────────────┘ └───────────────────────┘ └─────────────────┘
🤝 Contributing
Contributions are welcome! See CONTRIBUTING.md (maintainer releases, binary checksums) and the contribution guide. Pull requests and issues: GitHub.
✨ Contributors
Huge thanks to all contributors for making this project better!
This roster is maintained with all-contributors.
To add someone, update .all-contributorsrc and
regenerate the README table, or use the all-contributors bot/CLI from a PR.
More detail: docs/contributing/contributors.mdx.
📖 Learn More
- Flutter DevTools Documentation
- Dart VM Service Protocol
- Flutter DevTools RPC Constants (I guess and hope they are correct:))
Star History
<a href="https://www.star-history.com/?type=date&repos=Arenukvern%2Fmcp_flutter"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=Arenukvern/mcp_flutter&type=date&theme=dark&legend=top-left" /> <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=Arenukvern/mcp_flutter&type=date&legend=top-left" /> <img alt="Star History Chart" src="https://api.star-history.com/chart?repos=Arenukvern/mcp_flutter&type=date&legend=top-left" /> </picture> </a>📄 License
MIT - Feel free to use in your projects!
Flutter and Dart are trademarks of Google LLC.
Related MCP servers

A secured scoped SSH MCP server for executing safe read-only diagnostic DevOps / SysOps commands
MCP server for Argo RPG Platform — connects AI assistants to campaign data via OAuth2

io.github.Arielbs/rosetta-mcp-server
AI-powered Rosetta/PyRosetta protein modeling and Biotite translation for computational biology.

Strava Training MCP
Connect Strava training data to Claude for training load analysis and activity insights
End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.

Browsegrab
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.


