stop-recipe
AI agents invoke stop-recipe to trigger actions in Workato 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 recipe is an Execute-category action: it triggers an external operation (halting automation workflows) whose effects depend on arguments (which recipe to stop). While not destructive (reversible via restart), it has significant blast radius in an automation/workflow context—an agent could inadvertently halt critical business processes, impacting dependent systems and activities.
From the tool's definition Tool name 'stop-recipe' indicates it stops/halts a running recipe in Workato, which triggers an external operation with effects that depend on which recipe is targeted.
Attacks that exploit this kind of access
stop-recipe. It is categorised as a Execute tool in the Workato MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Workato MCP Server MCP server in PolicyLayer and add a rule for stop-recipe: 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 Workato MCP Server. Nothing to install.
stop-recipe 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-recipe 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-recipe. 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-recipe is provided by the Workato MCP Server MCP server (jacobgoren-sb/workato-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 →