manage_goals · Pelaris MCP: Risk & Policy

WHAT IT DOES

What manage_goals does on Pelaris

AI agents use manage_goals 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 manage_goals needs a policy

The tool modifies fitness goal records (create, update, complete) which are standard write operations. Completing or updating a goal does not irreversibly destroy data—goals can be modified or recreated. Listing goals is a read sub-operation. The severity is low because misuse would only affect personal fitness tracking data with no cascading system or financial impact.

From the tool's definition Tool description states 'Create, update, complete, or list your training goals' — these are reversible data modifications typical of write operations. No data is permanently deleted, no financial transactions occur, and no arbitrary code execution is involved.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

manage_goals Rate-limited

manage_goals 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": {
    "manage_goals": {
      "limits": [
        {
          "counter": "manage_goals_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 manage_goals

What does the manage_goals tool do? +

Create, update, complete, or list your training goals. Supports race events, body composition targets, and performance milestones. 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 manage_goals? +

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

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

Can I rate-limit manage_goals? +

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

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

manage_goals 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.