AI agents call two_actors_on_screen to retrieve information from MCP TMDB without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve information about actors who appeared together in films. It performs a data lookup against TMDB with no indication of modification, deletion, or execution capabilities. This is a read-only retrieval tool with minimal risk—worst-case misuse would return unwanted but harmless movie database information.
From the tool's definition Tool name 'two_actors_on_screen' and sibling tools (filmography_actor_genre, filmography_crew_genre, two_movies, two_people) all indicate data retrieval operations from TMDB.
Attacks that exploit this kind of access
two_actors_on_screen. It is categorised as a Read tool in the MCP TMDB MCP Server, which means it retrieves data without modifying state.
Register the MCP TMDB MCP server in PolicyLayer and add a rule for two_actors_on_screen: 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 TMDB. Nothing to install.
two_actors_on_screen 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 two_actors_on_screen 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 two_actors_on_screen. 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.
two_actors_on_screen is provided by the MCP TMDB MCP server (leonardogilrodriguez/mcp-tmdb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →