AI agents call get_workouts_count to retrieve information from Hevy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries a count metric with no side effects. The 'get_' prefix and lack of mutating keywords (create, delete, update) confirm read-only semantics. Even with an empty description, the function name and context among fitness tracking tools strongly suggests a simple data retrieval with minimal blast radius if misused.
From the tool's definition Tool name 'get_workouts_count' indicates a retrieval operation that queries aggregate data; empty description limits full context but naming pattern aligns with sibling tools like 'get_exercise_history', 'get_routine', which are read operations.
Documented attack patterns abuse exactly the kind of access get_workouts_count gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hevy, and nothing reaches the server without passing your rules. This is the rule we recommend for get_workouts_count:
{
"version": "1",
"default": "deny",
"tools": {
"get_workouts_count": {}
}
}get_workouts_count 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.
get_workouts_count. It is categorised as a Read tool in the Hevy MCP Server, which means it retrieves data without modifying state.
Register the Hevy MCP server in PolicyLayer and add a rule for get_workouts_count: 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.
get_workouts_count 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 get_workouts_count 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 get_workouts_count. 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.
get_workouts_count is provided by the Hevy MCP server (tomtorggler/hevy-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Hevy, 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.
17 Hevy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.