AI agents call audit_website 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 retrieves and analyzes publicly accessible website data to produce a scorecard. It only reads/fetches information about a target website and returns findings — no data is modified, deleted, or created. Misuse potential is low since it only performs read-only analysis.
From the tool's definition Run a deterministic 5-pillar audit on any website... Returns a 0-100 score with specific findings. Free, no API key, instant.
Attacks that exploit this kind of access
Run a deterministic 5-pillar audit on any website (Performance, SEO, Mobile, Security, AEO). Returns a 0-100 score with specific findings. Free, no API key, instant. 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 audit_website: 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.
audit_website 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 audit_website 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 audit_website. 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.
audit_website 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 →