Medium Risk

connect_app

Connect to a running Flutter App VM Service using specific URI. [USE WHEN] • You have a specific VM Service URI (ws://...) • Reconnecting to a known app instance [ALTERNATIVES] • If you don't have URI: use scan_and_connect() to auto-find • If app not running: use launch_app() to start it [AUTO...

Accepts URL/endpoint input (uri); Single-target operation

Part of the Flutter Skill MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

flutter-skill Write Risk 2/5

AI agents use connect_app to create or modify resources in Flutter Skill. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call connect_app repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Flutter Skill.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

io-github-ai-dashboad-flutter-skill.yaml
tools:
  connect_app:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full Flutter Skill policy for all 13 tools.

Tool Name connect_app
Category Write
Risk Level Medium

View all 13 tools →

Agents calling write-class tools like connect_app have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

What does the connect_app tool do? +

Connect to a running Flutter App VM Service using specific URI. [USE WHEN] • You have a specific VM Service URI (ws://...) • Reconnecting to a known app instance [ALTERNATIVES] • If you don't have URI: use scan_and_connect() to auto-find • If app not running: use launch_app() to start it [AUTO-FIX] If project_path is provided, automatically checks and fixes missing configuration: • Adds flutter_skill dependency to pubspec.yaml if missing • Adds FlutterSkillBinding initialization to main.dart if missing [MULTI-SESSION] Returns a session_id that can be used to target this specific app in subsequent tool calls. Omitting session_id in other tools will use the active session.. It is categorised as a Write tool in the Flutter Skill MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on connect_app? +

Add a rule in your Intercept YAML policy under the tools section for connect_app. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Flutter Skill MCP server.

What risk level is connect_app? +

connect_app is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit connect_app? +

Yes. Add a rate_limit block to the connect_app rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block connect_app completely? +

Set action: deny in the Intercept policy for connect_app. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides connect_app? +

connect_app is provided by the Flutter Skill MCP server (flutter-skill). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Flutter Skill

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.