Run a Fresh AI Visibility Scan

Read the saved score before you use a weekly run. After approval, the agent asks each tracked question on ChatGPT, Perplexity, and Google AI. It shows changes in scores, mentions, and sources.

Paste this into Claude, Codex, Cursor, ChatGPT, or another coding agent. The website, the expected output, and the approval boundary are already written in. First run? Complete the one-time setup; your agent can handle that too.

This is the sequence the agent follows. It reads data on its own. You approve each send or change.

1. 01

   Check before you spend

   Run get_ai_visibility for the stored snapshot and its run date. Reading is free and never spends a run.

2. 02

   Run the scan

   Run run_ai_visibility_scan to ask every tracked question now. Paid plans, one run per website per week.

3. 03

   Read the new answers

   Read the fresh score, which answers mention your site now, and the pages each platform cites.

4. 04

   Diff two runs

   Run diff_ai_visibility_runs for the score delta, gained and lost mentions, and new sources behind answers that named the site.

5. 05

   Pick the next move

   Run find_link_exchanges to turn a lost mention or a strong new cited source into one relevant exchange.

The exact MCP tool calls behind the prompt. Your agent runs these against the verifieddr server; the ones that send anything still stop for your approval.

# 1. The stored snapshot first (free, never spends a run)get_ai_visibility { site: "yourwebsite.com" } # 2. Ask every tracked question now (paid, one run per site per week)run_ai_visibility_scan { site: "yourwebsite.com" } # 3. Compare the fresh run against the previous onediff_ai_visibility_runs { site: "yourwebsite.com", from: "2026-07-01", to: "2026-08-01" } # 4. Turn a gap into one outreach movefind_link_exchanges { site: "yourwebsite.com" }