AI VisibilityGenerative AI SamplingActive in MCP

Discover Ai Citations

discover_ai_citations(topic: string, platform?: enum)

Which sources AI cites in your category (Google AI Overview).

Lists the most frequently cited domains in generative AI answers (Google AI Overviews and ChatGPT) for a given market vertical.

Input Parameters

2 arguments
ParameterTypeRequirementDefault / ConstraintsDescription
topicstringrequired
none
The category or topic to check AI-citation sources for.
platformenumoptional
default: googlegoogle | chat_gpt
google = Google AI Overview; chat_gpt = ChatGPT Search.

Return Envelope (OFE / 1.0)

Open Fact Envelope

Every response adheres to the strict ofe/1.0 envelope schema, returning verified data, typed facts, entity references, and follow-up tool suggestions:

data Payload

Lists the most frequently cited domains in generative AI answers (Google AI Overviews and ChatGPT) for a given market vertical.

coverage & Freshness

Reports returned count vs total items, observation timestamp as_of, and scope notes. Evaluated live per request.

resources (Dataset Exports)

If a query yields high row counts (e.g. >1,000 queries in Search Console), full unpaginated tables are persisted to R2 and linked as an mcpseo:// URI for follow-up retrieval via export_dataset.

next_actions

Provides suggested follow-up tool calls with pre-filled arguments so your AI agent can navigate from discovery to detailed inspection autonomously.

Emitted Facts & Entities

Knowledge Graph

Typed Facts

Facts emitted in the facts[] array with provenance receipts:

Fact TypeClaim DescriptionEmitted Data Fields
ai_visibility.citation_sourceDomain cited in AI answers with mention count and citation rank.
domainrankmentionsai_search_volume
core.data_freshnessObservation timestamp and platform identifier.
platformobserved_at

Registered Entities

Entities registered in the entities[] array to establish subject relationships:

domain

Cited source domains.

Request & Response Examples

Live MCP Payloads

Exact JSON schemas transmitted over Model Context Protocol (stdio or HTTP SSE transport):

1. Client Tool Invocation

discover_ai_citations request.json
{
  "tool": "discover_ai_citations",
  "arguments": {
    "topic": "developer productivity tools",
    "platform": "google"
  }
}

2. Server Envelope Response

discover_ai_citations response.json
{
  "schema_version": "ofe/1.0",
  "domain": "ai_visibility",
  "data": {
    "topic": "developer productivity tools",
    "platform": "google"
  },
  "facts": [
    {
      "type": "ai_visibility.citation_source",
      "subject": [
        "urn:domain:linear.app"
      ],
      "data": {
        "domain": "linear.app",
        "mentions": 18,
        "rank": 1
      },
      "provenance": {
        "source_class": "ai_answer",
        "method": "ai_answer_citations",
        "confidence": 0.5,
        "observed_at": "2026-09-24T00:00:00Z",
        "cache_hit": false
      }
    }
  ],
  "entities": [
    {
      "id": "urn:domain:linear.app",
      "kind": "domain",
      "label": "linear.app"
    }
  ],
  "coverage": {
    "returned": 1,
    "total": null,
    "as_of": "2026-09-24T00:00:00Z",
    "scope_note": null
  },
  "deltas": [],
  "resources": [],
  "next_actions": [
    {
      "tool": "inspect_ai_visibility",
      "args": {
        "domain": "linear.app"
      },
      "use_when": "inspect brand share of voice vs competitors"
    }
  ]
}

LLM Agent Workflow

Claude & Cursor Integration
Step 1

Prompt Trigger

"Which sources does Google AI Overview cite most often for 'developer productivity tools'?"
Step 2

Agent Decision & Reasoning

The agent identifies top authoritative domains cited by LLM answer engines, which informs content syndication and digital PR strategies.

Step 3

Recommended Follow-up Tools

Provenance Guarantees & Error Handling

Reliability
Source Classai_answer
Inspection Methodai_answer_citations
OFE Calibration Score0.50 (OFE 1.0 scale)
Cache DurationNone (Live)

Every fact emitted by Vouched includes source_class, method, observed_at ISO timestamp, and a published confidence score. LLM agents can inspect these citations to distinguish first-party verified facts (e.g. Search Console) from modeled competitor estimates.

Billing & API Keys

Paid market data, on Pro and Team. A call typically costs about $0.12 per call of market data, so Pro's included $4 covers roughly 33 calls. Self-hosted, it uses your own DataForSEO key and bills you directly, with nothing added. See pricing for what each tool costs.

More AI Visibility Tools

1 sibling tools
Self-host on GitHub (MIT)Try on Cloud plan