AI agents invoke schedule_workflow to trigger actions in Crosswalk. 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.
This tool schedules and triggers recurring automated workflows using cron-like execution. It causes external operations to be triggered on a schedule, which falls under Execute. The blast radius is medium — a misconfigured schedule could repeatedly trigger job cache refreshes or other workflows at unintended intervals, but it doesn't directly delete data or move money.
From the tool's definition Schedule a recurring non-sampling workflow... Run via cron +
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Schedule a recurring non-sampling workflow (e.g., refresh job cache every Monday). Run via cron +. It is categorised as a Execute tool in the Crosswalk MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Crosswalk MCP server in PolicyLayer and add a rule for schedule_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 Crosswalk. Nothing to install.
schedule_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 schedule_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 schedule_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.
schedule_workflow is provided by the Crosswalk MCP server (mohakgarg5/crosswalk-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 →