Stop or kill a running UiPath job.
AI agents invoke stop_job to trigger actions in UiPath MCP Server. 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.
Stopping a job is an active intervention in a running process that has immediate operational consequences. While not destructive (the job's data remains), it is definitively Execute category because it triggers external operations and changes system state in ways that depend on the specific argument (job ID).
From the tool's definition Tool name is 'stop_job' with description 'Stop or kill a running UiPath job.' This directly triggers an external operation (stopping an active job in UiPath Orchestrator) whose effects depend on which job argument is provided.
Attacks that exploit this kind of access
Stop or kill a running UiPath job. It is categorised as a Execute tool in the UiPath MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the UiPath MCP Server MCP server in PolicyLayer and add a rule for stop_job: 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 UiPath MCP Server. Nothing to install.
stop_job 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 stop_job 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 stop_job. 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.
stop_job is provided by the UiPath MCP Server MCP server (lokimcpuniverse/uipath-mcp-server). 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 →