AI agents use plex_mark_watched to create or update resources in Arr Suite MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Arr Suite MCP Server environment.
Marking media as watched is a reversible state modification (Write category) rather than destructive deletion or irreversible action. However, it could affect user experience and viewing history if applied incorrectly at scale. Severity is medium because while the action is reversible and has limited blast radius, bulk misuse could corrupt viewing history across multiple users on a shared Plex instance.
From the tool's definition Tool is named 'plex_mark_watched' with description 'Mark media as watched'. This modifies metadata state on a Plex media server, changing the watched status of media items.
Documented attack patterns abuse exactly the kind of access plex_mark_watched gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Arr Suite MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for plex_mark_watched:
{
"version": "1",
"default": "deny",
"tools": {
"plex_mark_watched": {
"limits": [
{
"counter": "plex_mark_watched_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}plex_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.
Free to start. No card required.
Mark media as watched. It is categorised as a Write tool in the Arr Suite MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Arr Suite MCP Server MCP server in PolicyLayer and add a rule for plex_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 Arr Suite MCP Server. Nothing to install.
plex_mark_watched is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the plex_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.
Set action: deny in the PolicyLayer policy for plex_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.
plex_mark_watched is provided by the Arr Suite MCP Server MCP server (shaktech786/arr-suite-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Arr Suite MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
25 Arr Suite MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.