AI agents call get_weekly_debrief 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 retrieves and displays aggregated training data (session completion, highlights, improvements, next week forecast) without creating, modifying, deleting, or executing any operations. It is purely informational and presents no risk of unintended side effects.
From the tool's definition Tool name 'get_weekly_debrief' and description 'View your weekly training summary' indicate data retrieval only. Verbs 'View' and 'summary' describe read-only operations with no state modification, deletion, or code execution.
Attacks that exploit this kind of access
View your weekly training summary — session completion, highlights, areas for improvement, and next week. 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_weekly_debrief: 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_weekly_debrief 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_weekly_debrief 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_weekly_debrief. 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_weekly_debrief 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 →