AI agents invoke servicenow_custom_api to trigger actions in Servicenow Api. 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.
The tool name suggests it calls custom/arbitrary ServiceNow API endpoints. Without a description, the exact behavior is unknown, but 'custom API' implies executing arbitrary operations against ServiceNow which could span read, write, or destructive actions. Given the potential blast radius of arbitrary API calls in an enterprise ITSM system, Execute is the most appropriate category at high severity.
From the tool's definition Tool name 'servicenow_custom_api' - description is empty and uninformative
Documented attack patterns abuse exactly the kind of access servicenow_custom_api gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Servicenow Api, and nothing reaches the server without passing your rules. This is the rule we recommend for servicenow_custom_api:
{
"version": "1",
"default": "deny",
"tools": {
"servicenow_custom_api": {
"limits": [
{
"counter": "servicenow_custom_api_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}servicenow_custom_api 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.
Free to start. No card required.
servicenow_custom_api. It is categorised as a Execute tool in the Servicenow Api MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Servicenow Api MCP server in PolicyLayer and add a rule for servicenow_custom_api: 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 Api. Nothing to install.
servicenow_custom_api is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the servicenow_custom_api 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.
Set action: deny in the PolicyLayer policy for servicenow_custom_api. 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.
servicenow_custom_api is provided by the Servicenow Api MCP server (knuckles-team/servicenow-api). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Servicenow Api, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 Servicenow Api tools catalogued and risk-classified — across an index of 43,000+ MCP servers.