AI agents use add_user_ratings to create or update resources in Trakt — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Trakt environment.
This tool creates or modifies user ratings on Trakt.tv, which is reversible (ratings can be updated or removed). It qualifies as Write rather than Read (modifies data) or Destructive (changes are not permanent/irreversible). The medium severity reflects that misuse could modify a user's entertainment preferences and history, but the impact is localized to rating data without financial or cascading effects.
From the tool's definition Tool name 'add_user_ratings' indicates creating or modifying user rating data. The empty description limits certainty, but the sibling tools (add_to_history, add_user_watchlist, checkin_to_show) all perform Write operations on user account data.
Documented attack patterns abuse exactly the kind of access add_user_ratings gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trakt, and nothing reaches the server without passing your rules. This is the rule we recommend for add_user_ratings:
{
"version": "1",
"default": "deny",
"tools": {
"add_user_ratings": {
"limits": [
{
"counter": "add_user_ratings_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_user_ratings 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.
add_user_ratings. It is categorised as a Write tool in the Trakt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Trakt MCP server in PolicyLayer and add a rule for add_user_ratings: 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 Trakt. Nothing to install.
add_user_ratings 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 add_user_ratings 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 add_user_ratings. 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.
add_user_ratings is provided by the Trakt MCP server (wwiens/trakt_mcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 77 Trakt tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
77 Trakt tools catalogued and risk-classified — across an index of 42,500+ MCP servers.