send_feedback · Pelaris MCP: Risk & Policy

WHAT IT DOES

What send_feedback does on Pelaris

AI agents use send_feedback 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.

WHY IT NEEDS A POLICY

Why send_feedback needs a policy

The tool creates new feedback records without destructive side effects. While it modifies the system state by adding feedback data, this is reversible and non-invasive. It poses minimal risk even if misused—sending unwanted or spam feedback would merely clutter the feedback database rather than compromise sensitive fitness data, delete user information, or trigger financial transactions.

From the tool's definition Tool name is 'send_feedback' and description states it allows users to 'Share feedback about the coaching experience'. This creates or records feedback data in the system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_feedback Rate-limited

send_feedback stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_feedback": {
      "limits": [
        {
          "counter": "send_feedback_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Pelaris, so you can run agents against it safely.

FAQ

Questions about send_feedback

What does the send_feedback tool do? +

Share feedback about the coaching experience to help improve tool quality and accuracy. 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.

How do I enforce a policy on send_feedback? +

Register the Pelaris MCP server in PolicyLayer and add a rule for send_feedback: 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.

What risk level is send_feedback? +

send_feedback is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send_feedback? +

Yes. Add a rate_limit block to the send_feedback 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.

How do I block send_feedback completely? +

Set action: deny in the PolicyLayer policy for send_feedback. 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.

What MCP server provides send_feedback? +

send_feedback 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.