launch_desktop_app
Launch a desktop command or Flatpak app in the active Steam Deck desktop session.
This record as markdown: /tools/mcp-control-plane/launch-desktop-app.md
What launch_desktop_app does on Mcp Control Plane
AI agents invoke launch_desktop_app to trigger actions in Mcp Control Plane. 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.
Why launch_desktop_app is rated High
This tool executes arbitrary commands or applications on a Steam Deck desktop session. An AI agent could use this to run malware, exfiltrate data, modify system settings, or compromise the device. The blast radius is critical because desktop command execution on a gaming/automation device can affect system integrity, data, and connected services.
From the tool's definition Tool description states it 'Launch[es] a desktop command or Flatpak app in the active Steam Deck desktop session.' The verb 'launch' combined with ability to execute arbitrary 'desktop command' or app represents code/command execution whose effects depend on…
Attacks that exploit this kind of access
The rule that runs launch_desktop_app safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Control Plane, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For launch_desktop_app, this is the rule to start with:
launch_desktop_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Control Plane, apply this rule, and every launch_desktop_app call is checked against it from then on.
Questions about launch_desktop_app
Launch a desktop command or Flatpak app in the active Steam Deck desktop session. It is categorised as a Execute tool in the Mcp Control Plane MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Control Plane MCP server in PolicyLayer and add a rule for launch_desktop_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 Mcp Control Plane. Nothing to install.
launch_desktop_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_desktop_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_desktop_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_desktop_app is provided by the Mcp Control Plane MCP server (albertik322-sudo/mcp-control-plane). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Control Plane, and thousands of servers like it.
Across the catalogue