AI agents call adcreative_get to retrieve information from Meta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves ad creative metadata from Meta's Graph API by creative ID. It queries data without modifying, deleting, or executing operations. The read-only server constraint and GET HTTP method confirm no side effects. Misuse risk is limited to unauthorized data access (information exposure), which is low severity without financial or destructive capability.
From the tool's definition Tool name 'adcreative_get' and description 'GET /{creative_id}' indicate a simple retrieval operation. Server is explicitly described as 'Read-only MCP server' for Meta Graph API.
Attacks that exploit this kind of access
GET /{creative_id}. It is categorised as a Read tool in the Meta MCP Server, which means it retrieves data without modifying state.
Register the Meta MCP server in PolicyLayer and add a rule for adcreative_get: 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 Meta. Nothing to install.
adcreative_get 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 adcreative_get 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 adcreative_get. 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.
adcreative_get is provided by the Meta MCP server (nourpups/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 →