ml_train_incident_classifier
Trigger training of the incident classification ML solution. [Write]
This record as markdown: /tools/tedorigawa001-servicenow-mcp/ml-train-incident-classifier.md
What ml_train_incident_classifier does on ServiceNow-MCP
AI agents invoke ml_train_incident_classifier to trigger actions in ServiceNow-MCP. 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 ml_train_incident_classifier is rated High
Although labeled '[Write]' in the description, the tool's actual function—triggering ML model training—is an Execute action. It launches an external operation (ML training) whose effects depend on the training data and configuration.
From the tool's definition 'Trigger training of the incident classification ML solution' indicates execution of a machine learning training pipeline, which is a computational operation with side effects that modifies the state of an ML model.
Attacks that exploit this kind of access
The rule that runs ml_train_incident_classifier safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ServiceNow-MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ml_train_incident_classifier, this is the rule to start with:
ml_train_incident_classifier 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 ServiceNow-MCP, apply this rule, and every ml_train_incident_classifier call is checked against it from then on.
Questions about ml_train_incident_classifier
Trigger training of the incident classification ML solution. [Write]. It is categorised as a Execute tool in the ServiceNow-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ServiceNow MCP server in PolicyLayer and add a rule for ml_train_incident_classifier: 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.
ml_train_incident_classifier 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 ml_train_incident_classifier 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 ml_train_incident_classifier. 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.
ml_train_incident_classifier 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.
More on ServiceNow, and thousands of servers like it.
Across the catalogue