Intelligently sample and analyze pages based on an audit plan. Use this AFTER plan_audit to analyze representative pages from each route type. For a site with 500k job pages, instead of crawling all of them, this will: - Sample 30-50 job detail pages (random + oldest + newest) - Sample 10-20 cate...
AI agents call sample_pages to retrieve information from SEO Audit MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
sample_pages retrieves and analyzes existing page data to produce reporting outputs. It queries page content and metadata, performs SEO analysis computations, and returns findings without creating, modifying, deleting, or executing any changes to the site or its data. This is a classic Read category tool with low blast radius if misused by an AI agent.
From the tool's definition Tool performs analysis and sampling of pages with returns including 'detailed analysis', 'aggregated issues', and 'findings' — all read-only outputs. Verbs used: 'sample', 'analyze', 'returns' data.
Attacks that exploit this kind of access
Intelligently sample and analyze pages based on an audit plan. Use this AFTER plan_audit to analyze representative pages from each route type. For a site with 500k job pages, instead of crawling all of them, this will: - Sample 30-50 job detail pages (random + oldest + newest) - Sample 10-20 category landing pages - Sample 10-20 location pages - Sample company pages, static pages, etc. Returns: - Detailed analysis of each sampled page - Aggregated issues per route type - Cross-cutting findings (% missing titles, schema errors, etc.) - Common issues ranked by frequency This approach finds template-level issues that affect all pages of that type. It is categorised as a Read tool in the SEO Audit MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SEO Audit MCP Server MCP server in PolicyLayer and add a rule for sample_pages: 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 SEO Audit MCP Server. Nothing to install.
sample_pages 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 sample_pages 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 sample_pages. 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.
sample_pages is provided by the SEO Audit MCP Server MCP server (richarddillman/seo-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 →