AI agents use create-routine to create or update resources in Routine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Routine environment.
This tool creates new routines (custom tools) by composing actions from other MCP tools. While creation is reversible (routines can be deleted via sibling delete-routine tool), the ability to create tools that can then invoke other MCP tools presents moderate risk if an AI agent creates routines with unintended side effects.
From the tool's definition Tool description states "Create a custom routine" which is a create operation, and sibling tools include "delete-routine" and "update-routine" indicating this is part of a reversible data creation workflow.
Attacks that exploit this kind of access
Create a custom routine from recently run actions. Inspect recently run tools. It is categorised as a Write tool in the Routine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Routine MCP server in PolicyLayer and add a rule for create-routine: 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.
create-routine 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 create-routine 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 create-routine. 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.
create-routine is provided by the Routine MCP server (mquan/mcp-routine). 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 →