Creates an A/B test (ad study) to compare campaigns or ad sets. Args: - ad_account_id (string): Ad account ID (e.g., act_123456789) - name (string): Study name - description (string, optional): Study description - start_time (string): ISO 8601 start time - end_time (string): ISO 8601 end time - t...
AI agents use meta_create_ad_study to create or update resources in Meta MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meta MCP Server environment.
This tool creates a new ad study/A/B test configuration in Meta's advertising platform. This is a write operation that creates new data structures and configurations but does not delete, destroy, execute arbitrary code, or move money. While it affects ad campaigns (potentially impacting spend allocation), the core action is configuration creation.
From the tool's definition Tool 'creates' an A/B test (ad study) via meta_create_ad_study with parameters for name, description, time range, test cells, and confidence level. The description explicitly states it 'Creates an A/B test', which is a reversible data creation operation.
Documented attack patterns abuse exactly the kind of access meta_create_ad_study gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Meta MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for meta_create_ad_study:
{
"version": "1",
"default": "deny",
"tools": {
"meta_create_ad_study": {
"limits": [
{
"counter": "meta_create_ad_study_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}meta_create_ad_study stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Creates an A/B test (ad study) to compare campaigns or ad sets. Args: - ad_account_id (string): Ad account ID (e.g., act_123456789) - name (string): Study name - description (string, optional): Study description - start_time (string): ISO 8601 start time - end_time (string): ISO 8601 end time - type (enum): SPLIT_TEST or HOLDOUT - cells (array): Test cells, each with name, treatment_percentage, and optional campaign_ids/adset_ids - confidence_level (number, default 95): Statistical confidence level (e.g., 90, 95, 99) Returns: The created study ID. It is categorised as a Write tool in the Meta MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Meta MCP Server MCP server in PolicyLayer and add a rule for meta_create_ad_study: 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 MCP Server. Nothing to install.
meta_create_ad_study is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the meta_create_ad_study 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 meta_create_ad_study. 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.
meta_create_ad_study is provided by the Meta MCP Server MCP server (oliverames/meta-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Meta MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
200 Meta MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.