Search the COROS exercise catalog (~383 strength exercises). Filter by name, muscle group, body part, and/or equipment. Returns exercise names, muscles, equipment, and default sets/reps.
AI agents call search_exercises to retrieve information from Coros Workout without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward query operation that retrieves and filters exercise data. It has no ability to create, modify, delete, or execute external operations. The worst-case misuse would be retrieving irrelevant exercise data, which poses minimal risk. Classification as Read is appropriate.
From the tool's definition Tool searches and returns data from an exercise catalog with no modification capability. Description states it 'returns exercise names, muscles, equipment, and default sets/reps' — purely informational retrieval with no side effects.
Documented attack patterns abuse exactly the kind of access search_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 search_exercises:
{
"version": "1",
"default": "deny",
"tools": {
"search_exercises": {}
}
}search_exercises is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search the COROS exercise catalog (~383 strength exercises). Filter by name, muscle group, body part, and/or equipment. Returns exercise names, muscles, equipment, and default sets/reps. It is categorised as a Read tool in the Coros Workout MCP Server, which means it retrieves data without modifying state.
Register the Coros Workout MCP server in PolicyLayer and add a rule for search_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.
search_exercises is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_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 search_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.
search_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.