Open a macOS application by name. Examples:
AI agents invoke open_application to trigger actions in Computer Use 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.
Opening an application triggers an external process on the OS. An AI agent could open arbitrary applications (e.g., terminal emulators, browsers, system utilities), which can have significant side effects depending on what is launched. This is an Execute-category action with high severity due to the broad blast radius of launching arbitrary macOS applications.
From the tool's definition 'Open a macOS application by name' — launches external applications on the host system
Attacks that exploit this kind of access
Open a macOS application by name. Examples:. It is categorised as a Execute tool in the Computer Use MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Computer Use MCP Server MCP server in PolicyLayer and add a rule for open_application: 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 Computer Use MCP Server. Nothing to install.
open_application 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 open_application 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 open_application. 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.
open_application is provided by the Computer Use MCP Server MCP server (syedazharmbnr1/computer-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →