run_atf_test

THE RISK

High Risk

Why run_atf_test needs a policy

ATF tests are scripts that perform actions on the ServiceNow instance. While the tool itself is narrowly scoped to executing a pre-defined test by sys_id (reducing severity vs. arbitrary code execution), the underlying test content is arbitrary and its effects are unpredictable. An AI agent could execute tests that modify data, trigger workflows, or affect system state.

From the tool's definition 'Execute a single ServiceNow ATF (Automated Test Framework) test' — ATF tests can contain arbitrary logic, API calls, and side effects that depend on the test content and system state. Execution of tests is inherently an Execute operation.

Documented attack patterns abuse exactly the kind of access run_atf_test gives an agent:

POLICY

How to control run_atf_test

PolicyLayer is an MCP gateway — it sits between your AI agents and Now Sdk Ext, and nothing reaches the server without passing your rules. This is the rule we recommend for run_atf_test:

policy.json

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

run_atf_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.

Create a free account and register Now Sdk Ext — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Now Sdk Ext tools

Destructive cancel_flow Cancel a running or paused flow execution by its context ID. Destructive query_delete_records Find records matching an encoded query and delete them all. Execute aggregate_grouped Run aggregate functions (COUNT, AVG, MIN, MAX, SUM) grouped by a field on any Execute execute_action Execute a ServiceNow Flow Designer action by scoped name. Execute execute_flow Execute a published ServiceNow Flow Designer flow by scoped name. Execute execute_script Execute JavaScript on a ServiceNow instance using Scripts - Background Execute execute_subflow Execute a ServiceNow Flow Designer subflow by scoped name. Execute run_atf_test_suite Execute a ServiceNow ATF test suite and wait for all tests to complete.

All 86 Now Sdk Ext tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Now Sdk Ext → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_atf_test

What does the run_atf_test tool do? +

Execute a single ServiceNow ATF (Automated Test Framework) test by its sys_id. It is categorised as a Execute tool in the Now Sdk Ext MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_atf_test? +

Register the Now Sdk Ext MCP server in PolicyLayer and add a rule for run_atf_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 Now Sdk Ext. Nothing to install.

What risk level is run_atf_test? +

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

Can I rate-limit run_atf_test? +

Yes. Add a rate_limit block to the run_atf_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 run_atf_test completely? +

Set action: deny in the PolicyLayer policy for run_atf_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 run_atf_test? +

run_atf_test is provided by the Now Sdk Ext MCP server (sonisoft-cnanda/now-sdk-ext-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Now Sdk Ext tool call.

Start from Now Sdk Ext, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →