AI agents use create_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 creates a routine in the Hevy fitness app, which is a reversible operation (routines can be modified or deleted). It modifies user data but does not execute arbitrary code, delete data permanently, or involve financial transactions. The empty description lowers confidence slightly, but the naming pattern and server context strongly suggest a Write classification.
From the tool's definition Tool name is 'create_routine' and server description states it can 'Log workouts, manage routines, track body measurements, browse exercises'. The 'create_' prefix indicates data creation.
Attacks that exploit this kind of access
create_routine. 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: 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 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 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 →