Audit sales copy for Gumroad/Landing pages and give a score.
AI agents call audit_copy to retrieve information from Growth Hacker MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Auditing and scoring sales copy is a read/analysis operation. It takes input text, evaluates it, and returns feedback (score, power words, CTA analysis). No data is created, modified, deleted, or any financial transaction initiated. Consistent with sibling tools that also perform text generation/formatting without destructive side effects.
From the tool's definition 'Audit sales copy' and 'give a score' — the tool analyzes and evaluates existing content, returning feedback and a score with no side effects.
Attacks that exploit this kind of access
Audit sales copy for Gumroad/Landing pages and give a score. It is categorised as a Read tool in the Growth Hacker MCP MCP Server, which means it retrieves data without modifying state.
Register the Growth Hacker MCP server in PolicyLayer and add a rule for audit_copy: 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 Growth Hacker MCP. Nothing to install.
audit_copy is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the audit_copy 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 audit_copy. 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.
audit_copy is provided by the Growth Hacker MCP server (samusilv/growth-hacker-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 →