mark_unwatched · Mcp Plex MCP: Risk & Policy

WHAT IT DOES

What mark_unwatched does on Mcp Plex

AI agents use mark_unwatched to create or update resources in Mcp Plex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Plex environment.

WHY IT NEEDS A POLICY

Why mark_unwatched needs a policy

This tool modifies user state (watch progress) on media items, making it a Write operation rather than Read. It is not Destructive because the change is reversible—marking something as watched again undoes the action.

From the tool's definition mark_unwatched resets watch progress on media items, which is a reversible modification of metadata state (watch status). The tool name and description clearly indicate it modifies data ('Mark...

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_unwatched Rate-limited

mark_unwatched 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": {
    "mark_unwatched": {
      "limits": [
        {
          "counter": "mark_unwatched_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 Mcp Plex, so you can run agents against it safely.

FAQ

Questions about mark_unwatched

What does the mark_unwatched tool do? +

Mark a media item as unwatched, resetting its watch progress. It is categorised as a Write tool in the Mcp Plex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_unwatched? +

Register the Mcp Plex MCP server in PolicyLayer and add a rule for mark_unwatched: 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 Mcp Plex. Nothing to install.

What risk level is mark_unwatched? +

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

Can I rate-limit mark_unwatched? +

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

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

mark_unwatched is provided by the Mcp Plex MCP server (obrien-matthew/mcp-plex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.