AI agents use update_user to create or update resources in Snow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Snow environment.
This tool modifies user records in ServiceNow, which are business-critical data but the change is reversible (an updated user can be reverted to a previous state). It falls under Write category rather than Destructive since updates can be undone.
From the tool's definition Tool name is 'update_user' and description states 'Update an existing user record.' The verb 'update' indicates reversible modification of data.
Documented attack patterns abuse exactly the kind of access update_user gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Snow, and nothing reaches the server without passing your rules. This is the rule we recommend for update_user:
{
"version": "1",
"default": "deny",
"tools": {
"update_user": {
"limits": [
{
"counter": "update_user_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_user stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update an existing user record. It is categorised as a Write tool in the Snow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Snow MCP server in PolicyLayer and add a rule for update_user: 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 Snow. Nothing to install.
update_user is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_user 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 update_user. 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.
update_user is provided by the Snow MCP server (shunyaai/snow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Snow, 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.
88 Snow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.