AI agents invoke launch_app to trigger actions in Claude Pascal MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
launch_app executes an application, triggering external operations with unpredictable effects depending on what application is launched and what state the system is in. This falls under Execute rather than Write because it runs processes rather than creating/modifying persistent data. Severity is high due to potential for unauthorized application execution affecting system state, data access, or user operations.
From the tool's definition Tool is part of Pascal/Delphi compilation and application execution system; sibling tools include adb_launch_app, adb_push, adb_install which collectively enable running arbitrary applications.
Documented attack patterns abuse exactly the kind of access launch_app gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Pascal MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for launch_app:
{
"version": "1",
"default": "deny",
"tools": {
"launch_app": {
"limits": [
{
"counter": "launch_app_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}launch_app stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
launch_app. It is categorised as a Execute tool in the Claude Pascal MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Pascal MCP Server MCP server in PolicyLayer and add a rule for launch_app: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Pascal MCP Server. Nothing to install.
launch_app is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the launch_app rule in your PolicyLayer 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.
Set action: deny in the PolicyLayer policy for launch_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.
launch_app is provided by the Claude Pascal MCP Server MCP server (tina4stack/claude-pascal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Pascal MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
53 Claude Pascal MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.