Open an app in the default web browser. If the app is not currently being served,
AI agents invoke app_open to trigger actions in Goose App Maker MCP. 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.
This tool executes an external operation by opening a web browser and potentially starting a web server if the app isn't already being served. It triggers side effects beyond simple data retrieval, making it Execute rather than Read.
From the tool's definition 'Open an app in the default web browser' and 'If the app is not currently being served' implies triggering external operations (launching browser, potentially starting a server)
Attacks that exploit this kind of access
Open an app in the default web browser. If the app is not currently being served,. It is categorised as a Execute tool in the Goose App Maker MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Goose App Maker MCP server in PolicyLayer and add a rule for app_open: 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 Goose App Maker MCP. Nothing to install.
app_open 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 app_open 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 app_open. 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.
app_open is provided by the Goose App Maker MCP server (michaelneale/goose-app-maker-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 →