Verify the Create button is enabled, then click it.
AI agents invoke click_create to trigger actions in Suno Autopilot 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.
Clicking the Create button submits a song generation request to an external service (Suno) via browser automation. This is an externally triggered operation whose effects depend on prior inputs (lyrics, style) loaded into the form. It is an Execute action with high severity because it causes an irreversible external API/service call that consumes Suno credits and creates content on a third-party platform.
From the tool's definition 'Verify the Create button is enabled, then click it' — triggers browser automation to submit a song creation request to Suno
Attacks that exploit this kind of access
Verify the Create button is enabled, then click it. It is categorised as a Execute tool in the Suno Autopilot MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Suno Autopilot MCP server in PolicyLayer and add a rule for click_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 Suno Autopilot MCP. Nothing to install.
click_create 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 click_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 click_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.
click_create is provided by the Suno Autopilot MCP server (voidreapercmxcix/suno-autopilot-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 →