Get the most recent workout matching type or tag.
AI agents call get_last_workout to retrieve information from MCP Logger without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries workout data from the fitness tracking database to retrieve the most recent entry matching specified criteria. It performs a read-only operation that does not create, modify, delete, or execute external actions. The fitness metrics retrieved pose minimal security risk even if accessed inappropriately, as they are personal health data without financial or destructive implications.
From the tool's definition Tool name 'get_last_workout' and description 'Get the most recent workout matching type or tag' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the most recent workout matching type or tag. It is categorised as a Read tool in the MCP Logger MCP Server, which means it retrieves data without modifying state.
Register the MCP Logger MCP server in PolicyLayer and add a rule for get_last_workout: 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 MCP Logger. Nothing to install.
get_last_workout 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_last_workout 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_last_workout. 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_last_workout is provided by the MCP Logger MCP server (johnzolton/mcp-logger). 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 →