Skip a recurring task occurrence without completing it. Creates the next occurrence.
AI agents use skip_recurring_task to create or update resources in Streamline MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Streamline MCP environment.
This tool modifies task state in a structured way (marking one occurrence as skipped and generating the next), but the changes are reversible (the user could undo or re-schedule tasks). It does not permanently delete data (Destructive), execute arbitrary code (Execute), or move financial value (Financial).
From the tool's definition The tool description states it will 'skip a recurring task occurrence' and 'create the next occurrence' — both modify the state of task data by altering which occurrence is active/pending, which constitutes a reversible write operation.
Attacks that exploit this kind of access
Skip a recurring task occurrence without completing it. Creates the next occurrence. It is categorised as a Write tool in the Streamline MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Streamline MCP server in PolicyLayer and add a rule for skip_recurring_task: 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 Streamline MCP. Nothing to install.
skip_recurring_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the skip_recurring_task 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 skip_recurring_task. 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.
skip_recurring_task is provided by the Streamline MCP server (rostehea/streamline-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 →