AI agents call get_icon_usage_examples to retrieve information from Heroicons 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 example data about how icons are used. It is a pure read operation with no side effects. The severity is low because it only retrieves informational content with no ability to affect systems, data integrity, or operations. The confidence is high given the clear read-only nature indicated by the function name and description.
From the tool's definition The tool 'get_icon_usage_examples' retrieves usage examples for an icon, with the verb 'get' and no indication of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Get usage examples for an icon. It is categorised as a Read tool in the Heroicons MCP Server, which means it retrieves data without modifying state.
Register the Heroicons MCP server in PolicyLayer and add a rule for get_icon_usage_examples: 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 Heroicons. Nothing to install.
get_icon_usage_examples 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_icon_usage_examples 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_icon_usage_examples. 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_icon_usage_examples is provided by the Heroicons MCP server (seeyangzhi/heroicons-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 →