Recommend movies from liked and disliked titles with provider-aware scoring, match reasons, and watch-out notes
AI agents call recommend_from_taste_profile to retrieve information from Tmdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval and data analysis tool. It takes user taste preferences as input and returns curated movie suggestions with explanatory metadata. No data is created, modified, or deleted; no external code is executed; and no financial transactions occur. The tool fits the 'Read' category as it queries and returns information with no side effects.
From the tool's definition The tool 'recommend_from_taste_profile' retrieves and returns movie recommendations based on input preferences.
Documented attack patterns abuse exactly the kind of access recommend_from_taste_profile gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tmdb, and nothing reaches the server without passing your rules. This is the rule we recommend for recommend_from_taste_profile:
{
"version": "1",
"default": "deny",
"tools": {
"recommend_from_taste_profile": {}
}
}recommend_from_taste_profile is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Recommend movies from liked and disliked titles with provider-aware scoring, match reasons, and watch-out notes. It is categorised as a Read tool in the Tmdb MCP Server, which means it retrieves data without modifying state.
Register the Tmdb MCP server in PolicyLayer and add a rule for recommend_from_taste_profile: 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 Tmdb. Nothing to install.
recommend_from_taste_profile is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the recommend_from_taste_profile 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 recommend_from_taste_profile. 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.
recommend_from_taste_profile is provided by the Tmdb MCP server (laksh-star/mcp-server-tmdb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tmdb, 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.
24 Tmdb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.