Publish a completed changeset so it can be retrieved from the remote instance.
AI agents invoke publish_changeset to trigger actions in Snow. 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.
Publishing a changeset triggers an external operation that deploys code/configuration changes to a remote ServiceNow instance. This is an execution-class action with significant blast radius — pushing bad code or configurations to production could break services.
From the tool's definition 'Publish a completed changeset so it can be retrieved from the remote instance'
Documented attack patterns abuse exactly the kind of access publish_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 publish_changeset:
{
"version": "1",
"default": "deny",
"tools": {
"publish_changeset": {
"limits": [
{
"counter": "publish_changeset_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} publish_changeset 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.
Publish a completed changeset so it can be retrieved from the remote instance. It is categorised as a Execute tool in the Snow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Snow MCP server in PolicyLayer and add a rule for publish_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.
publish_changeset 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 publish_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 publish_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.
publish_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.