mark_watched · Mcp Plex MCP: Risk & Policy

WHAT IT DOES

What mark_watched does on Mcp Plex

AI agents use mark_watched 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_watched needs a policy

This tool creates or modifies data reversibly - it sets a watched flag on a media item, which is a state change that can be undone (the item can be marked unwatched). It has no side effects beyond updating the media item's metadata, no data is deleted or destroyed, no code is executed, and no financial transactions occur. It falls squarely into the Write category as a metadata modification operation.

From the tool's definition Tool name is 'mark_watched' and description states 'Mark a media item as fully watched.' This modifies metadata state of a media item by changing its watch status.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_watched Rate-limited

mark_watched 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_watched": {
      "limits": [
        {
          "counter": "mark_watched_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_watched

What does the mark_watched tool do? +

Mark a media item as fully watched. 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_watched? +

Register the Mcp Plex MCP server in PolicyLayer and add a rule for mark_watched: 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_watched? +

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

Can I rate-limit mark_watched? +

Yes. Add a rate_limit block to the mark_watched 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_watched completely? +

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

mark_watched 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.