update_profile · Pelaris MCP: Risk & Policy

WHAT IT DOES

What update_profile does on Pelaris

AI agents use update_profile 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 update_profile needs a policy

This tool creates or modifies user profile data reversibly. It updates preferences rather than executing code, deleting data, or performing financial transactions. The blast radius is minimal—misconfiguration of training preferences has low impact on system integrity or user safety. Classified as Write with low severity.

From the tool's definition Tool description states 'Update your training preferences' which modifies user profile data (equipment, available days, session duration, experience level).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_profile Rate-limited

update_profile 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": {
    "update_profile": {
      "limits": [
        {
          "counter": "update_profile_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 update_profile

What does the update_profile tool do? +

Update your training preferences — equipment, available days, session duration, experience level, and more. 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 update_profile? +

Register the Pelaris MCP server in PolicyLayer and add a rule for update_profile: 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 update_profile? +

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

Can I rate-limit update_profile? +

Yes. Add a rate_limit block to the update_profile 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 update_profile completely? +

Set action: deny in the PolicyLayer policy for update_profile. 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 update_profile? +

update_profile 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.