AI mention research report

See where a named brand or product appears in a provider-indexed set of AI answers, which domains are cited and whether retained questions overlap with searches already associated with your site. The report keeps indexed research separate from live prompt checks.

Install and run the report

Install the CLI once, then run seo start to connect your site and Google data. After setup you can run this report yourself or ask your agent to run it.

Runafter install

Install the SEO CLI globally.

npm i -g seo

Run setup after installation.

seo start

Research one target in a bounded provider-indexed AI dataset.

seo reports run ai-mention-research --params '{"target":{"label":"Example Analytics"},"surface":"google-ai-overview","countryCode":"GB","languageCode":"en","location":{"code":2826}}' --json

What you get from this report

Compare provider-indexed mentions, cited domains, and bounded question samples for one AI surface and market, then add Search Console overlap when you own the site.

Best for: You need mention and citation evidence beyond referral traffic or technical eligibility.
Needs: Provider-indexed AI mention data
You get: Target and competitor mention metrics, source-domain evidence, and at most 25 retained question samples for one surface, location, and language.
Use next: Turn SEO queries into AI prompts

What you need before you run it

This report uses dataForSEO LLM Mentions metrics, cited source domains, and bounded question samples for the exact surface, location, and language. optional retained Search Console query and landing-page rows for a property you own.

Provider-indexed AI mention data

Provides target metrics, cited source domains, question samples, observation dates, model names, and the exact surface and market.

Optional Search Console query rows

Adds bounded first-party query and landing-page evidence for a property you own.

Explicit target and comparison set

Defines one named target, its aliases, and at most five named competitors measured in the same provider request.

What the AI search evidence checks

The report uses observed crawl, search or referral evidence. It keeps technical access, assistant visibility and recorded visits as separate questions.

Keeps mention metrics and question samples in separate evidence states, so a failed sample request does not erase successful metrics.

Calculates mention share only across supplied targets, marks cited URLs from an optional owned domain, and applies a bounded lexical overlap heuristic to retained Search Console rows.

Reports cache status, price evidence, actual cost, provider task ids, row caps, invalid rows, processing bounds, warnings, and partial states.

Keep access, visibility and visits separate

A page can be crawlable without appearing in an answer. A mention can also happen without sending a measurable visit. Read the evidence for the question this report actually answers.

Read first	Why it matters
Result	Target and competitor mention metrics, source-domain evidence, and at most 25 retained question samples for one surface, location, and language.
More detail	Owned citation flags, optional first-party query matches, repeated question terms, cautious programmatic data-source briefs, findings, caveats, and next steps.
Read it with	Read source status, coverage, observation time, cache, cost, and warnings first. Then compare target metrics, retained questions, citations, and first-party overlap without blending them into one score.

What the result cannot prove

Provider-indexed records are not live prompt observations or a complete census. Search Console overlap is lexical and bounded, so a match does not prove shared intent and no match does not prove a gap.

Read source status, coverage, observation time, cache, cost, and warnings first. Then compare target metrics, retained questions, citations, and first-party overlap without blending them into one score. Check existing pages, source rights, useful variation, and representative records before expanding a programmatic template.

Run this on a measured weekly or monthly cadence only when the indexed dataset supports the selected surface and market. Keep the target set, aliases and location stable so changes are comparable, and use refresh only when newer provider evidence is worth another paid request.

Use a different report for these jobs

You need the answer returned by a fixed prompt right now. Use ai-prompt-observations with the exact surface, model, market label, time, answer, and citations instead. You need a complete census, a universal visibility score, sentiment, or proof that an AI product never mentions a target.

You need the current answer for a fixed prompt rather than an indexed research dataset.

Run AI prompt observations. Keep the prompt, surface, requested and effective model, market label, settings, time, answer, and citations together so a later compatible observation can be compared.

AI prompt observation report

You need measured visits from known AI products.

Run AI referrals. It reads Google Analytics referral sessions and landing pages instead of inferring traffic from mention records.

AI referral traffic report

You only need technical crawl, index, or snippet eligibility evidence.

Run AI search readiness. It checks technical controls without claiming that an AI product mentioned or cited the site.

AI search readiness audit

Use the report with an agent or in code

The command above is enough for most work. These options let an agent, script or application run the same report with explicit input and structured output.

Use the report catalog when an agent, script or CI job needs predictable JSON instead of the normal terminal output. Check the current input first, then run the report with the validated parameters.

Check the current input before the agent or script runs the report.

seo reports describe ai-mention-research --json

Once the input is valid, run the report through the report catalog.

seo reports run ai-mention-research --params '{"target":{"label":"Example Analytics","aliases":["Example"]},"competitors":[{"label":"Competitor Cloud"}],"domain":"example.com","surface":"google-ai-overview","countryCode":"GB","languageCode":"en","location":{"code":2826},"site":"sc-domain:example.com","sampleLimit":10}' --json

An MCP agent follows the same two-step flow. It inspects the current schema, fills the required fields and only then runs the report.

Ask the MCP server for the current report input.

{
  "id": "ai-mention-research"
}

Run the report after the agent has checked and filled the input.

{
  "id": "ai-mention-research",
  "params": {
    "target": {
      "label": "Example Analytics",
      "aliases": [
        "Example"
      ]
    },
    "competitors": [
      {
        "label": "Competitor Cloud"
      }
    ],
    "domain": "example.com",
    "surface": "google-ai-overview",
    "countryCode": "GB",
    "languageCode": "en",
    "location": {
      "code": 2826
    },
    "site": "sc-domain:example.com",
    "sampleLimit": 10
  }
}

Install the package in a Node 22 project when your application needs to run the report directly. The result includes the same evidence, warnings and limits returned through the CLI and MCP server.

Add the SEO package to your project.

npm install seo

Run the report from your TypeScript application.

import { executeReport } from 'seo/mcp'

const result = await executeReport(
  'ai-mention-research',
  {
  "target": {
    "label": "Example Analytics",
    "aliases": [
      "Example"
    ]
  },
  "competitors": [
    {
      "label": "Competitor Cloud"
    }
  ],
  "domain": "example.com",
  "surface": "google-ai-overview",
  "countryCode": "GB",
  "languageCode": "en",
  "location": {
    "code": 2826
  },
  "site": "sc-domain:example.com",
  "sampleLimit": 10
},
)

console.log(result)

What to do next

Inspect the exact market, cited pages and retained questions before acting on a mention difference. Check existing first-party pages, then use a fixed prompt observation only for the small question set where a current answer would change the decision.

01Inspect cited pages and current results for the questions that would change a decision.
02Use ai-prompt-observations for a small stable question set before making claims about current answers.
03Check existing pages, source rights, useful variation, and representative records before expanding a programmatic template.

Turn real Search Console queries into prompts for repeatable AI answer monitoring.

AI search query report

Run a small fixed set of prompts against explicit current AI models, retain the evidence locally, and compare only like-for-like observations.

AI prompt observation report

See which known AI products sent referral sessions recorded by Google Analytics and which landing pages received them.

AI referral traffic report

Extend observed template and query-cluster evidence with optional keyword discovery, live results, competitor patterns, costs, and data-source checks.

Programmatic SEO opportunities

Create a focused brief for one existing page from its own search queries and the content observed on the live URL.

Content optimization report

Sources used by this report

These primary sources define the provider data or search controls used by the result.