create_routine
AI agents use create_routine to create or update resources in FitnessMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FitnessMCP environment.
This tool creates new routine data structures, which is a reversible Write operation. It modifies user fitness data by adding a new routine, but this action can be undone (deleted). Severity is medium because misuse could clutter user data or create unwanted routines, but no data is destroyed and no external operations are triggered.
From the tool's definition Tool name 'create_routine' indicates creation of a new routine object. Sibling tools 'create_exercise_template', 'create_routine_folder', and 'create_workout' all perform reversible data creation operations.
Attacks that exploit this kind of access
create_routine. It is categorised as a Write tool in the FitnessMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fitness 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 FitnessMCP. 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 Fitness MCP server (senoj100-alt/fitnessmcp). 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 →