run_atf_suite

Execute an ATF test suite (requires ATF_ENABLED=true)

SERVERServiceNow MCP Server SOURCE@aartiq/servicenow-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity verified Pull the record →

This record as markdown: /tools/servicenow-mcp-server/run-atf-suite.md

WHAT IT DOES

What run_atf_suite does on ServiceNow MCP Server

AI agents invoke run_atf_suite to trigger actions in ServiceNow MCP Server. 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.

RISK

Why run_atf_suite is rated High

This tool triggers execution of an Automated Test Framework (ATF) suite, which runs code and can have side effects depending on what the test suite does. While test suites are typically intended for testing, they can modify data, call external APIs, or perform other operations. The execution of arbitrary or misconfigured tests poses a risk if an AI agent triggers them without proper understanding of their effects.

From the tool's definition Tool name explicitly states 'run_atf_suite' and description says 'Execute an ATF test suite'. The verb 'Execute' combined with running a test suite indicates code execution.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs run_atf_suite safely

PolicyLayer is an MCP gateway: it sits between your AI agents and ServiceNow MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_atf_suite, this is the rule to start with:

run_atf_suite Rate-limited

run_atf_suite 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": {
    "run_atf_suite": {
      "limits": [
        {
          "counter": "run_atf_suite_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect ServiceNow MCP Server, apply this rule, and every run_atf_suite call is checked against it from then on.

FAQ

Questions about run_atf_suite

What does the run_atf_suite tool do? +

Execute an ATF test suite (requires ATF_ENABLED=true). It is categorised as a Execute tool in the ServiceNow MCP Server 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_suite? +

Register the ServiceNow MCP Server MCP server in PolicyLayer and add a rule for run_atf_suite: 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 ServiceNow MCP Server. Nothing to install.

What risk level is run_atf_suite? +

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

Can I rate-limit run_atf_suite? +

Yes. Add a rate_limit block to the run_atf_suite 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_suite completely? +

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

run_atf_suite is provided by the ServiceNow MCP Server MCP server (@aartiq/servicenow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on ServiceNow MCP Server, and thousands of servers like it.

This server

All 365 ServiceNow MCP Server tools → High-risk tools on this server →

Across the catalogue

shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →