AI agents use create_routine_folder to create or update resources in Hevy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hevy environment.
Creating a folder is a reversible write operation that modifies the user's routine organization structure without executing external commands, deleting data, or involving financial transactions. The impact is limited to adding a new organizational element. Severity is low because routine folder creation has minimal blast radius—at worst, it creates organizational clutter that can be easily removed.
From the tool's definition Tool name includes 'create_' and description states 'Create a new folder to organize routines.' This is a data creation action that creates a new organizational container.
Attacks that exploit this kind of access
Create a new folder to organize routines. It is categorised as a Write tool in the Hevy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hevy MCP server in PolicyLayer and add a rule for create_routine_folder: 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 Hevy. Nothing to install.
create_routine_folder 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_folder 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_folder. 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_folder is provided by the Hevy MCP server (srdjancodes/hevy-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 →