AI agents call taskUnplanned to retrieve information from Routine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries task data filtered by planning status. There is no indication it modifies, deletes, executes external actions, or commits financial transactions. It is a straightforward data retrieval operation with no side effects, matching the Read category. Severity is low because misuse would only expose or list existing task information.
From the tool's definition Tool name 'taskUnplanned' and description 'Unplanned tasks' indicates retrieval of task data without modification or deletion. The verb 'unplanned' suggests querying tasks filtered by their unplanned status, consistent with a read/list operation.
Attacks that exploit this kind of access
Unplanned tasks. It is categorised as a Read tool in the Routine MCP Server, which means it retrieves data without modifying state.
Register the Routine MCP server in PolicyLayer and add a rule for taskUnplanned: 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 Routine. Nothing to install.
taskUnplanned is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the taskUnplanned 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 taskUnplanned. 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.
taskUnplanned is provided by the Routine MCP server (routineco/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 →