snow_start_workflow
⚠️ LEGACY: Start a workflow on a record (deprecated - ServiceNow recommends Flow Designer). Workflows run asynchronously.
This record as markdown: /tools/serac/snow-start-workflow.md
What snow_start_workflow does on Serac
AI agents invoke snow_start_workflow to trigger actions in Serac. 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.
Why snow_start_workflow is rated High
Starting a workflow executes arbitrary business logic on a ServiceNow record, with effects determined by the workflow definition rather than the tool itself. This is Execute rather than Write because workflows can perform complex multi-step operations (approvals, notifications, state transitions, integrations) that go beyond simple data modification.
From the tool's definition Tool description states 'Start a workflow on a record' — this triggers execution of automated business processes in ServiceNow. The phrase 'Workflows run asynchronously' confirms external effects occur beyond the caller's direct control.
Attacks that exploit this kind of access
The rule that runs snow_start_workflow safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Serac, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For snow_start_workflow, this is the rule to start with:
snow_start_workflow 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Serac, apply this rule, and every snow_start_workflow call is checked against it from then on.
Questions about snow_start_workflow
⚠️ LEGACY: Start a workflow on a record (deprecated - ServiceNow recommends Flow Designer). Workflows run asynchronously. It is categorised as a Execute tool in the Serac MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Serac MCP server in PolicyLayer and add a rule for snow_start_workflow: 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 Serac. Nothing to install.
snow_start_workflow 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 snow_start_workflow 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 snow_start_workflow. 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.
snow_start_workflow is provided by the Serac MCP server (serac-labs/serac). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Serac, and thousands of servers like it.
Across the catalogue