AI agents call compare_websites to retrieve information from Fdl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a comparative analysis of website metrics and returns scores and grades. It retrieves and processes existing data from two websites without creating, modifying, deleting, or executing any side effects. The action is purely informational (Read category).
From the tool's definition Tool name 'compare_websites' and description 'Compare two websites side-by-side. Returns scores, grades, and a winner.' indicate retrieval and analysis of data with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Compare two websites side-by-side. Returns scores, grades, and a winner. It is categorised as a Read tool in the Fdl MCP Server, which means it retrieves data without modifying state.
Register the Fdl MCP server in PolicyLayer and add a rule for compare_websites: 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 Fdl. Nothing to install.
compare_websites 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_websites 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_websites. 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_websites is provided by the Fdl MCP server (nareshdevelop/fdl-mcp-server). 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 →