根据卡牌ID获取详细的炉石传说卡牌信息
AI agents call get_card_info to retrieve information from Hearthstone Decks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a card database for metadata and statistics. It has no side effects, cannot modify game state or user data, and poses minimal security risk even if an AI agent calls it repeatedly or with arbitrary card IDs. The operation is purely informational retrieval.
From the tool's definition Tool retrieves 'detailed card information' (卡牌信息) by card ID with no modification capability. The description uses 'get' and 'retrieve' semantics consistent with Read operations.
Attacks that exploit this kind of access
根据卡牌ID获取详细的炉石传说卡牌信息. It is categorised as a Read tool in the Hearthstone Decks MCP Server, which means it retrieves data without modifying state.
Register the Hearthstone Decks MCP server in PolicyLayer and add a rule for get_card_info: 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 Hearthstone Decks. Nothing to install.
get_card_info 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_card_info 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_card_info. 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_card_info is provided by the Hearthstone Decks MCP server (yinshawnrao/hearthstone-decks-mcp). 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 →