strava_star_segment
AI agents use strava_star_segment to create or update resources in FitnessMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FitnessMCP environment.
Strava has a 'star segment' feature that marks a segment as a favorite. This is a reversible write operation (you can unstar it). The description is empty, so confidence is lowered. Based on naming conventions from Strava's API, starring a segment modifies user data but is not destructive or financial.
From the tool's definition Tool name 'strava_star_segment' — 'star' implies bookmarking/favoriting a segment on Strava, which is a reversible write action (toggle star on/off).
Attacks that exploit this kind of access
strava_star_segment. It is categorised as a Write tool in the FitnessMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fitness MCP server in PolicyLayer and add a rule for strava_star_segment: 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.
strava_star_segment is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the strava_star_segment 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 strava_star_segment. 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.
strava_star_segment 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 →