Get all vendor icons for a concept (e.g., 'kubernetes' returns the K8s icon from AWS, Azure, and GCP).
AI agents call compare_icons to retrieve information from Tech Icons without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a catalog of icons and returns matching results. It has no side effects, does not modify data, does not execute code or commands, and does not involve financial transactions. It is purely informational retrieval, matching the 'Read' category definition of querying data with no side effects.
From the tool's definition Tool retrieves and returns vendor icons for a concept without modifying, deleting, or executing anything. Description states 'Get all vendor icons' — a retrieval operation.
Attacks that exploit this kind of access
Get all vendor icons for a concept (e.g., 'kubernetes' returns the K8s icon from AWS, Azure, and GCP). It is categorised as a Read tool in the Tech Icons MCP Server, which means it retrieves data without modifying state.
Register the Tech Icons MCP server in PolicyLayer and add a rule for compare_icons: 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 Tech Icons. Nothing to install.
compare_icons 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 compare_icons 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 compare_icons. 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.
compare_icons is provided by the Tech Icons MCP server (zhiweio/tech-icons). 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 →