ab_experiment_create · Yaver MCP: Risk & Policy

WHAT IT DOES

What ab_experiment_create does on Yaver

AI agents use ab_experiment_create to create or update resources in Yaver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.

PARAMETERS

Parameter	Type	Required
`key`	string	Yes
`name`	string	—
`metric`	string	—
`variants`	array	Yes

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why ab_experiment_create needs a policy

An AI agent can call ab_experiment_create faster than any human can review — one bad instruction and it creates or modifies resources in Yaver by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ab_experiment_create Rate-limited

ab_experiment_create 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ab_experiment_create": {
      "limits": [
        {
          "counter": "ab_experiment_create_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Yaver, so you can run agents against it safely.

FAQ

Questions about ab_experiment_create

What does the ab_experiment_create tool do? +

Create or update an A/B experiment. Variants are weighted (summed, normalised); bucketing is sticky per userId via SHA256. Metric is the event name that counts as a conversion. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does ab_experiment_create accept? +

ab_experiment_create accepts 4 parameters: key, name, metric, variants. Required: key, variants. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on ab_experiment_create? +

Register the Yaver MCP server in PolicyLayer and add a rule for ab_experiment_create: 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 Yaver. Nothing to install.

What risk level is ab_experiment_create? +

ab_experiment_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit ab_experiment_create? +

Yes. Add a rate_limit block to the ab_experiment_create 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.

How do I block ab_experiment_create completely? +

Set action: deny in the PolicyLayer policy for ab_experiment_create. 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.

What MCP server provides ab_experiment_create? +

ab_experiment_create is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.