execute_api_test · Decide Test MCP: Risk & Policy

WHAT IT DOES

What execute_api_test does on Decide Test MCP

AI agents invoke execute_api_test to trigger actions in Decide Test MCP. 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 execute_api_test needs a policy

This tool executes external API calls based on user-provided test cases and steps. While the execution is of 'predefined' steps rather than arbitrary code, it still triggers real API operations that can have side effects on external systems (create records, modify data, trigger workflows, etc.). The tool's effect depends on which API steps are selected and executed, making it an Execute risk.

From the tool's definition Tool description states 'Execute predefined API test steps' and 'Takes a test case and specific API steps to execute.' The verb 'execute' combined with the capability to run API test steps indicates this tool triggers external operations (API calls) whose…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_api_test Rate-limited

execute_api_test 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": {
    "execute_api_test": {
      "limits": [
        {
          "counter": "execute_api_test_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 Decide Test MCP, so you can run agents against it safely.

FAQ

Questions about execute_api_test

What does the execute_api_test tool do? +

Execute predefined API test steps. Takes a test case and specific API steps to execute. It is categorised as a Execute tool in the Decide Test MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_api_test? +

Register the Decide Test MCP server in PolicyLayer and add a rule for execute_api_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 Decide Test MCP. Nothing to install.

What risk level is execute_api_test? +

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

Can I rate-limit execute_api_test? +

Yes. Add a rate_limit block to the execute_api_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 execute_api_test completely? +

Set action: deny in the PolicyLayer policy for execute_api_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 execute_api_test? +

execute_api_test is provided by the Decide Test MCP server (k-n-t-lam/decide-test-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.