get_exercise_history
AI agents call get_exercise_history to retrieve information from FitnessMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves past exercise records from a fitness service (likely Hevy based on sibling tools). It is a read-only query operation that accesses user fitness data but does not create, modify, or delete anything. The blast radius of misuse is low—an AI agent could expose fitness history but cannot cause financial harm, delete data, or execute arbitrary operations.
From the tool's definition Tool name is 'get_exercise_history' which follows the 'get_*' pattern indicating data retrieval with no modification. The description is empty, but the name strongly implies querying historical exercise data without side effects.
Attacks that exploit this kind of access
get_exercise_history. It is categorised as a Read tool in the FitnessMCP MCP Server, which means it retrieves data without modifying state.
Register the Fitness 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 FitnessMCP. 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 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 →