AI agents call get_watching_decades 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 statistical data about the user's movie watching patterns grouped by decade. It performs a query operation on stored personal data without creating, modifying, deleting, or executing any external actions. The output is read-only summary information.
From the tool's definition Tool name 'get_watching_decades' and description 'Get decade breakdown across all watched movies. Returns each decade with movie count.' indicate retrieval and aggregation of personal viewing history data with no modification or side effects.
Attacks that exploit this kind of access
Get decade breakdown across all watched movies. Returns each decade with movie count. 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 get_watching_decades: 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.
get_watching_decades 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 get_watching_decades 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 get_watching_decades. 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.
get_watching_decades 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 →