AI agents use save_website_and_audit to create or update resources in Web Audit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Web Audit environment.
The tool creates/stores new audit records and website entries in an account (Write action). While it modifies system state by adding data, it is reversible (websites and audit reports can be deleted or modified later), distinguishing it from Destructive.
From the tool's definition Tool description states 'Add a website to the agent account' and 'persist the report for the web UI' — these are reversible creation/modification actions that create new records in the system.
Attacks that exploit this kind of access
Add a website to the agent account, run an audit, and persist the report for the web UI. It is categorised as a Write tool in the Web Audit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Web Audit MCP server in PolicyLayer and add a rule for save_website_and_audit: 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 Web Audit. Nothing to install.
save_website_and_audit is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_website_and_audit 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 save_website_and_audit. 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.
save_website_and_audit is provided by the Web Audit MCP server (sayuru-akash/web-audit-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 →