Medium Risk

create_ab_test

Create an A/B test on a link. Split traffic across 2–5 URL variants with configurable weights. Same visitor always sees the same variant (cookie-based sticky bucketing). Edge-speed redirects (<50ms). Requires Pro plan or above.

Part of the Clypt server.

create_ab_test can modify Clypt data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE CLYPT →

Free to start. No card required.

AI agents use create_ab_test to create or modify resources in Clypt. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call create_ab_test repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Clypt.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_ab_test": {
      "limits": [
        {
          "counter": "create_ab_test_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Clypt policy for all 16 tools.

Get this rule live on your own Clypt server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY CLYPT →

View all 16 tools →

These attack patterns abuse exactly the kind of access create_ab_test gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so create_ab_test only ever does what you allow.

SECURE CLYPT →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the create_ab_test tool do? +

Create an A/B test on a link. Split traffic across 2–5 URL variants with configurable weights. Same visitor always sees the same variant (cookie-based sticky bucketing). Edge-speed redirects (<50ms). Requires Pro plan or above.. It is categorised as a Write tool in the Clypt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_ab_test? +

Register the Clypt MCP server in PolicyLayer and add a rule for create_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 Clypt. Nothing to install.

What risk level is create_ab_test? +

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

Can I rate-limit create_ab_test? +

Yes. Add a rate_limit block to the create_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.

How do I block create_ab_test completely? +

Set action: deny in the PolicyLayer policy for create_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.

What MCP server provides create_ab_test? +

create_ab_test is provided by the Clypt MCP server (clypt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Clypt tool call.

Deterministic rules across all 16 Clypt tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.