AI agents use record_injury to create or update resources in Pelaris — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pelaris environment.
The tool writes a new injury entry to the user's profile and causes the training plan to be updated accordingly. Both actions are reversible (the record can be deleted, the plan readjusted), so this falls under Write rather than Execute or Destructive.
From the tool's definition 'Log an injury or pain point so your training plan adapts automatically' — creates a new injury record and triggers plan modification
Attacks that exploit this kind of access
Log an injury or pain point so your training plan adapts automatically. Returns a coaching note about how sessions will adjust. It is categorised as a Write tool in the Pelaris MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pelaris MCP server in PolicyLayer and add a rule for record_injury: 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.
record_injury 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 record_injury 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 record_injury. 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.
record_injury 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 →