AI agents call search_people 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.
Even though search_people only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Search for people (actors, directors, producers, crew) by name. Returns basic info including profile photo, known for department, and movies/TV shows they. 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 search_people: 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.
search_people 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 search_people 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 search_people. 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.
search_people is provided by the Tmdb MCP server (tmdb-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.