AI agents use update_routine 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.
This tool modifies user data (workout routines and their exercise composition) but the changes are reversible through subsequent updates. It does not delete data irreversibly, execute arbitrary code, or involve financial transactions.
From the tool's definition Tool description states 'Update an existing routine. Replaces all exercises.' The verb 'update' and 'replaces' indicate modification of existing data. The action is reversible—routines can be updated again to restore previous exercises.
Attacks that exploit this kind of access
Update an existing routine. Replaces all exercises. 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 update_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 Hevy. Nothing to install.
update_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 update_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 update_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.
update_routine 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 →