功能3: 地区浏览
AI agents call browse_by_province to retrieve information from University Rankings MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or filters existing university ranking data by province—a read-only operation with no side effects, data modification, code execution, or financial implications. The action is passive data retrieval, placing it solidly in the 'Read' category with low severity and low blast radius for misuse.
From the tool's definition Tool name 'browse_by_province' and description '地区浏览' (browse by region/province) indicates a retrieval/query operation that lists or filters university data by geographic location.
Attacks that exploit this kind of access
功能3: 地区浏览. It is categorised as a Read tool in the University Rankings MCP Server MCP Server, which means it retrieves data without modifying state.
Register the University Rankings MCP Server MCP server in PolicyLayer and add a rule for browse_by_province: 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 University Rankings MCP Server. Nothing to install.
browse_by_province 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_by_province 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_by_province. 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_by_province is provided by the University Rankings MCP Server MCP server (mouseminar/university_rankings_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 →