Create a new local Update Set (changeset).
AI agents use create_changeset 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 creates a new changeset/Update Set in ServiceNow, which is a write operation that creates a new object. While changesets can contain configuration changes, the creation itself is reversible—Update Sets can be modified, backed up, or deleted. This is not destructive (not irreversible), not financial, and not execute-level (doesn't run arbitrary code or trigger external operations directly).
From the tool's definition Tool name 'create_changeset' and description 'Create a new local Update Set (changeset)' explicitly indicate creation of a new object/record. Update Sets are reversible configurations in ServiceNow that can be modified or deleted.
Documented attack patterns abuse exactly the kind of access create_changeset 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 create_changeset:
{
"version": "1",
"default": "deny",
"tools": {
"create_changeset": {
"limits": [
{
"counter": "create_changeset_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_changeset 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.
Create a new local Update Set (changeset). 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 create_changeset: 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.
create_changeset 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 create_changeset 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 create_changeset. 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.
create_changeset 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.