test_webhook · Kula Ai MCP: Risk & Policy

WHAT IT DOES

What test_webhook does on Kula Ai

AI agents invoke test_webhook to trigger actions in Kula Ai. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why test_webhook needs a policy

This tool actively sends a network request to an external system (the webhook endpoint), which constitutes executing an external operation. It is not purely read (it causes side effects on the receiving end), not write (it doesn't persist data), and not destructive or financial. The blast radius is medium since it triggers external calls that could cause unintended side effects on the receiving service.

From the tool's definition 'Send a test payload to a webhook and wait for the delivery result' — triggers an external HTTP request to a registered webhook endpoint

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

test_webhook Rate-limited

test_webhook stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "test_webhook": {
      "limits": [
        {
          "counter": "test_webhook_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about test_webhook

What does the test_webhook tool do? +

Send a test payload to a webhook and wait for the delivery result. Polls until delivered or failed (30s timeout). It is categorised as a Execute tool in the Kula Ai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on test_webhook? +

Register the Kula Ai MCP server in PolicyLayer and add a rule for test_webhook: 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 Kula Ai. Nothing to install.

What risk level is test_webhook? +

test_webhook is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit test_webhook? +

Yes. Add a rate_limit block to the test_webhook 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 test_webhook completely? +

Set action: deny in the PolicyLayer policy for test_webhook. 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 test_webhook? +

test_webhook is provided by the Kula Ai MCP server (kula-ai/kula-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.