AI agents call get_coach_insight to retrieve information from Pelaris without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns coaching insights derived from existing training data. It has no side effects, does not create or modify user data, does not execute code or external operations, and does not involve financial transactions. The verb 'Get' confirms it is a retrieval operation.
From the tool's definition Tool name 'get_coach_insight' and description 'Get personalised coaching observations' indicate a retrieval/query operation that returns data-driven insights without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Get personalised coaching observations based on your recent training — consistency, fatigue, goal progress, and areas to focus on. It is categorised as a Read tool in the Pelaris MCP Server, which means it retrieves data without modifying state.
Register the Pelaris MCP server in PolicyLayer and add a rule for get_coach_insight: 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 Pelaris. Nothing to install.
get_coach_insight 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_coach_insight 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_coach_insight. 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_coach_insight is provided by the Pelaris MCP server (thedonk/pelaris-mcp-server). 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 →