AI agents call get_exercise_history 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.
This tool retrieves and queries exercise history data without creating, modifying, deleting, or executing operations. It is purely informational and has no side effects beyond returning existing data. The blast radius of misuse is minimal—an agent could view a user's past exercise data, which is a privacy concern but not destructive or dangerous.
From the tool's definition Tool name 'get_exercise_history' with description 'Get logged sets for a specific exercise across all workouts, newest first.' indicates retrieval of historical workout data with no modification or deletion.
Attacks that exploit this kind of access
Get logged sets for a specific exercise across all workouts, newest first. 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_exercise_history: 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_exercise_history 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_exercise_history 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_exercise_history. 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_exercise_history 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 →