Approves a change request. This finds the current user's approval record
AI agents use approve_change 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.
Approving a change request modifies data (approval status/records) but is reversible—approvals can be revoked, changed, or records updated. This is a Write operation, not Destructive. However, severity is high because approving a change in ServiceNow can trigger downstream workflow automation, deployments, or infrastructure changes that depend on that approval.
From the tool's definition Tool description states it 'Approves a change request,' which modifies the approval state of an existing change record. The context of ServiceNow change management indicates this creates or updates approval records, a reversible write operation.
Documented attack patterns abuse exactly the kind of access approve_change 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 approve_change:
{
"version": "1",
"default": "deny",
"tools": {
"approve_change": {
"limits": [
{
"counter": "approve_change_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}approve_change 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.
Approves a change request. This finds the current user's approval 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 approve_change: 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.
approve_change 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 approve_change 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 approve_change. 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.
approve_change 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.