List ad creatives inside an ad account.
AI agents call list_creatives 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.
The tool retrieves and lists existing ad creatives, which is a read-only operation. It queries data without creating, modifying, deleting, or executing external operations. Even in the context of a Meta Ads connector where some sibling tools are destructive (delete_ad, delete_ad_creative, delete_adset), this specific tool performs only data retrieval.
From the tool's definition Tool name is 'list_creatives' and description states 'List ad creatives inside an ad account' — this is a retrieval/query operation with no modification or side effects.
Attacks that exploit this kind of access
List ad creatives inside an ad account. 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 list_creatives: 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.
list_creatives 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 list_creatives 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 list_creatives. 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.
list_creatives 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 →