Refresh auth by extracting cookie from user
AI agents call tp_refresh_auth to retrieve information from TrainingPeaks-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read/retrieval operation—it extracts authentication credentials from the user's existing session to refresh authorization tokens. It does not create, modify, delete, or execute external operations with unpredictable effects. While handling auth credentials carries inherent sensitivity, the tool itself is fundamentally a Read operation that retrieves local session data.
From the tool's definition Tool name is 'tp_refresh_auth' and description states 'Refresh auth by extracting cookie from user'. The function retrieves/extracts an existing authentication cookie for session refresh purposes.
Attacks that exploit this kind of access
Refresh auth by extracting cookie from user. It is categorised as a Read tool in the TrainingPeaks-MCP MCP Server, which means it retrieves data without modifying state.
Register the TrainingPeaks- MCP server in PolicyLayer and add a rule for tp_refresh_auth: 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 TrainingPeaks-MCP. Nothing to install.
tp_refresh_auth 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 tp_refresh_auth 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 tp_refresh_auth. 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.
tp_refresh_auth is provided by the TrainingPeaks- MCP server (jamsusmaximus/trainingpeaks-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 →