Render a preview of an ad for a given placement (returns HTML iframe markup).
AI agents call preview_ad to retrieve information from Claude Meta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and renders a visual preview of an ad without modifying, deleting, or executing any external operations. It returns HTML markup for display purposes only, making it a Read operation with minimal security risk. The low severity reflects that preview generation has no adverse consequences on ads, campaigns, or financial systems.
From the tool's definition Tool description states 'Render a preview of an ad for a given placement (returns HTML iframe markup)' — the verb 'preview' and return of static HTML markup indicate read-only retrieval with no side effects.
Attacks that exploit this kind of access
Render a preview of an ad for a given placement (returns HTML iframe markup). It is categorised as a Read tool in the Claude Meta MCP Server, which means it retrieves data without modifying state.
Register the Claude Meta MCP server in PolicyLayer and add a rule for preview_ad: 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 Claude Meta. Nothing to install.
preview_ad 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 preview_ad 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 preview_ad. 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.
preview_ad is provided by the Claude Meta MCP server (maxx3250/claude-meta-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 →