manage_program · Pelaris MCP: Risk & Policy

WHAT IT DOES

What manage_program does on Pelaris

AI agents use manage_program 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_program needs a policy

Archiving data is a Write operation—it modifies state reversibly without destroying information. The tool does not permanently delete the program (which would be Destructive), nor does it execute arbitrary code or trigger financial transactions. The blast radius is low as archiving a fitness program has minimal downstream impact.

From the tool's definition Tool name 'manage_program' with description 'Archive a training program' indicates a reversible modification action. Archiving is a state change operation (marking as inactive) rather than permanent deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

manage_program Rate-limited

manage_program 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_program": {
      "limits": [
        {
          "counter": "manage_program_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_program

What does the manage_program tool do? +

Archive a training program. Use get_program_status to view programs first. 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_program? +

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

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

Can I rate-limit manage_program? +

Yes. Add a rate_limit block to the manage_program 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_program completely? +

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

manage_program 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.