Fetch the latest exercise catalog from COROS APIs and rebuild the local catalog. Requires authentication. Fetches exercises from the COROS API and i18n strings for human-readable names.
AI agents use update_exercises to create or update resources in Coros Workout — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Coros Workout environment.
The tool writes to local state (rebuilding a cached catalog) in a reversible manner. It does not delete or destroy data (Destructive), execute arbitrary code or commands (Execute), initiate financial transactions (Financial), or expose external systems to uncontrolled operations.
From the tool's definition Tool performs 'Fetch the latest exercise catalog from COROS APIs and rebuild the local catalog' — this modifies local cached data by updating it with fresh data from an external source.
Documented attack patterns abuse exactly the kind of access update_exercises gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Coros Workout, and nothing reaches the server without passing your rules. This is the rule we recommend for update_exercises:
{
"version": "1",
"default": "deny",
"tools": {
"update_exercises": {
"limits": [
{
"counter": "update_exercises_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_exercises stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fetch the latest exercise catalog from COROS APIs and rebuild the local catalog. Requires authentication. Fetches exercises from the COROS API and i18n strings for human-readable names. It is categorised as a Write tool in the Coros Workout MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Coros Workout MCP server in PolicyLayer and add a rule for update_exercises: 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 Coros Workout. Nothing to install.
update_exercises 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_exercises 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_exercises. 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_exercises is provided by the Coros Workout MCP server (rowlando/coros-workout-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Coros Workout, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Coros Workout tools catalogued and risk-classified — across an index of 43,000+ MCP servers.