映画の詳細情報（出演者、カテゴリ、在庫状況含む）を取得します。
AI agents call get_film_details to retrieve information from Sakila MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns film metadata (actors, categories, inventory status) without any side effects, state changes, or capability to modify data. It is purely informational retrieval, matching the Read category definition. Low severity due to absence of blast radius from misuse—an AI agent cannot cause harm by retrieving film details.
From the tool's definition Tool name 'get_film_details' and description indicate retrieval of film information including cast, category, and inventory status. No creation, modification, deletion, or execution capability indicated.
Attacks that exploit this kind of access
映画の詳細情報（出演者、カテゴリ、在庫状況含む）を取得します。. It is categorised as a Read tool in the Sakila MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sakila MCP Server MCP server in PolicyLayer and add a rule for get_film_details: 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 Sakila MCP Server. Nothing to install.
get_film_details 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_film_details 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_film_details. 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_film_details is provided by the Sakila MCP Server MCP server (mo3g4u/mcp-server-sample). 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 →