AI agents call browse_movies to retrieve information from Rewind without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters movie data from a personal collection without any capability to create, modify, delete, or execute external operations. The operations (filtering, sorting, pagination, returning results) are all non-destructive read queries. Severity is low because misuse would only expose existing personal movie data, not cause irreversible harm or trigger external side effects.
From the tool's definition Tool description explicitly states 'Browse' with 'filters', 'sorting', 'pagination', and 'returns' — all read-only query operations. No modify, delete, or execute language present. Verb 'browse' and 'returns' indicate data retrieval only.
Attacks that exploit this kind of access
Browse the movie collection with filters for genre, decade, director, and year. Supports sorting, pagination, and returns top-N posters. It is categorised as a Read tool in the Rewind MCP Server, which means it retrieves data without modifying state.
Register the Rewind MCP server in PolicyLayer and add a rule for browse_movies: 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 Rewind. Nothing to install.
browse_movies 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 browse_movies 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 browse_movies. 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.
browse_movies is provided by the Rewind MCP server (rewind-mcp-server). 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 →