Get full details of a subflow including its inputs, outputs, and actions
AI agents call get_subflow to retrieve information from ServiceNow-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata and configuration details about a ServiceNow subflow (inputs, outputs, actions). The verb 'Get' and absence of any modification language ('create', 'delete', 'execute', 'run') confirm this is a read-only operation. Blast radius is minimal—an AI agent querying subflow definitions cannot cause harm beyond accessing workflow metadata that likely has standard ServiceNow access controls.
From the tool's definition Tool name 'get_subflow' and description 'Get full details of a subflow including its inputs, outputs, and actions' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get full details of a subflow including its inputs, outputs, and actions. It is categorised as a Read tool in the ServiceNow-MCP MCP Server, which means it retrieves data without modifying state.
Register the ServiceNow- MCP server in PolicyLayer and add a rule for get_subflow: 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 ServiceNow-MCP. Nothing to install.
get_subflow is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_subflow 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 get_subflow. 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.
get_subflow is provided by the ServiceNow- MCP server (tedorigawa001/servicenow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →