AI agents call two_people 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.
Despite empty description, the naming pattern and context strongly indicate this retrieves data about connections between two individuals in the film database. The TMDB server is a read-only API wrapper with no capabilities to modify, delete, or execute operations. Confidence slightly reduced due to missing explicit description, but sibling tools provide strong contextual evidence of read-only retrieval.
From the tool's definition Tool name 'two_people' suggests querying relationships between two people; sibling tools like 'two_actors_on_screen' and 'two_movies' are clearly read-only data retrievals from TMDB; server purpose is to 'search for movie collaborations, actor filmographies,…
Attacks that exploit this kind of access
two_people. 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_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 MCP TMDB. Nothing to install.
two_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 two_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 two_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.
two_people 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 →