Get comprehensive guidance on setting up A/B tests for ad creatives. Provides best practices, testing strategies, and metrics to track for creative optimization.
AI agents call setup_ab_test to retrieve information from Meta Marketing API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the action-sounding name 'setup_ab_test', the description clearly states this tool only provides guidance, best practices, and metrics information. It does not actually create, configure, or execute an A/B test — it is purely an informational/advisory retrieval tool. Severity is low since misuse only returns guidance text with no side effects.
From the tool's definition 'Get comprehensive guidance on setting up A/B tests' and 'Provides best practices, testing strategies, and metrics to track' — the tool retrieves informational guidance rather than creating or modifying any resources.
Attacks that exploit this kind of access
Get comprehensive guidance on setting up A/B tests for ad creatives. Provides best practices, testing strategies, and metrics to track for creative optimization. It is categorised as a Read tool in the Meta Marketing API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Meta Marketing API MCP Server MCP server in PolicyLayer and add a rule for setup_ab_test: 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 Marketing API MCP Server. Nothing to install.
setup_ab_test 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 setup_ab_test 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 setup_ab_test. 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.
setup_ab_test is provided by the Meta Marketing API MCP Server MCP server (pythonando/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 →