List all your saved XERT workouts. Returns workout names, IDs, and last modified dates.
AI agents call xert-list-workouts to retrieve information from XERT Cycling Training without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays a list of existing workouts with metadata. It has no side effects, creates no new data, executes no operations, and cannot modify or delete anything. It is a straightforward read operation on the user's workout library.
From the tool's definition Tool description explicitly states it 'List[s] all your saved XERT workouts' and 'Returns workout names, IDs, and last modified dates' — purely retrieving/querying data with no modification capability.
Attacks that exploit this kind of access
List all your saved XERT workouts. Returns workout names, IDs, and last modified dates. It is categorised as a Read tool in the XERT Cycling Training MCP Server, which means it retrieves data without modifying state.
Register the XERT Cycling Training MCP server in PolicyLayer and add a rule for xert-list-workouts: 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 XERT Cycling Training. Nothing to install.
xert-list-workouts 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 xert-list-workouts 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 xert-list-workouts. 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.
xert-list-workouts is provided by the XERT Cycling Training MCP server (milofax/xert-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 →