从Bing壁纸获取随机壁纸，返回壁纸的URL、标题和描述信息
AI agents call get_random_wallpaper to retrieve information from MCP Project Query Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries an external service (Bing) and returns metadata (URL, title, description). It performs no modifications, deletions, code execution, or financial transactions. It is a safe read-only operation with minimal blast radius if invoked by an AI agent.
From the tool's definition Tool name 'get_random_wallpaper' and description indicate it 'retrieves random wallpaper' from Bing, returning 'URL, title and description information' — purely a data retrieval operation with no side effects.
Attacks that exploit this kind of access
从Bing壁纸获取随机壁纸，返回壁纸的URL、标题和描述信息. It is categorised as a Read tool in the MCP Project Query Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Project Query Server MCP server in PolicyLayer and add a rule for get_random_wallpaper: 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 Project Query Server. Nothing to install.
get_random_wallpaper 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_random_wallpaper 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_random_wallpaper. 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_random_wallpaper is provided by the MCP Project Query Server MCP server (sweetwisdom/mcp-demo). 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 →