app_create
AI agents use app_create to create or update resources in Goose App Maker MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Goose App Maker MCP environment.
This tool creates new web applications, which is a reversible write operation. Severity is high because created applications could host arbitrary code or content, and an AI agent could create malicious applications if misused. The empty description lowers confidence slightly, but the tool name and server context are clear.
From the tool's definition Tool name 'app_create' indicates creation of new applications. Server description confirms 'create, manage, and serve web applications' capability. Sibling tools (app_delete, app_serve, app_stop_server) show this is an application lifecycle management system.
Attacks that exploit this kind of access
app_create. It is categorised as a Write tool in the Goose App Maker MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Goose App Maker MCP server in PolicyLayer and add a rule for app_create: 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_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the app_create 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_create. 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_create 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 →