SERPPro / BYOKLive SERP SnapshotActive in MCP

Inspect Serp

inspect_serp(keyword: string, depth?: number)

Live SERP snapshot for one query.

Live Google search results snapshot returning both organic positions and non-organic SERP furniture (featured snippets, People Also Ask, AI Overviews).

Input Parameters

2 arguments

Parameter	Type	Requirement	Default / Constraints	Description
`keyword`	`string`	required	none	The search query to snapshot.
`depth`	`number`	optional	default: `20`Integer between 1 and 100	How many organic results deep to snapshot.

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

Live Google search results snapshot returning both organic positions and non-organic SERP furniture (featured snippets, People Also Ask, AI Overviews).

`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 Type	Claim Description	Emitted Data Fields
`serp.result`	Organic web result position, ranking domain, URL, and snippet title.	`positiondomainurltitle`
`serp.feature`	Special SERP features (featured_snippet, people_also_ask, ai_overview).	`feature_typepositiondomaintitle`

Registered Entities

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

domain

Domains appearing on the SERP.

page

Individual URLs appearing on the SERP.

Request & Response Examples

Live MCP Payloads

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

1. Client Tool Invocationinspect_serp request.json
{
  "tool": "inspect_serp",
  "arguments": {
    "keyword": "claude code mcp setup",
    "depth": 20
  }
}

2. Server Envelope Responseinspect_serp response.json
{
  "schema_version": "ofe/1.0",
  "domain": "serp",
  "data": {
    "keyword": "claude code mcp setup",
    "items_count": 14
  },
  "facts": [
    {
      "type": "serp.result",
      "subject": [
        "urn:page:https%3A%2F%2Fdocs.anthropic.com%2Fclaude-code%2Fmcp"
      ],
      "data": {
        "position": 1,
        "domain": "docs.anthropic.com",
        "url": "https://docs.anthropic.com/claude-code/mcp",
        "title": "Model Context Protocol in Claude Code"
      },
      "provenance": {
        "source_class": "live_serp",
        "method": "google_serp",
        "confidence": 0.85,
        "observed_at": "2026-09-24T00:00:00Z",
        "cache_hit": false
      }
    },
    {
      "type": "serp.feature",
      "subject": [
        "urn:domain:docs.anthropic.com"
      ],
      "data": {
        "feature_type": "featured_snippet",
        "position": 1,
        "domain": "docs.anthropic.com",
        "title": "Quickstart Guide"
      },
      "provenance": {
        "source_class": "live_serp",
        "method": "google_serp",
        "confidence": 0.65,
        "observed_at": "2026-09-24T00:00:00Z",
        "cache_hit": false
      }
    }
  ],
  "entities": [
    {
      "id": "urn:domain:docs.anthropic.com",
      "kind": "domain",
      "label": "docs.anthropic.com"
    },
    {
      "id": "urn:page:https%3A%2F%2Fdocs.anthropic.com%2Fclaude-code%2Fmcp",
      "kind": "page",
      "label": "https://docs.anthropic.com/claude-code/mcp"
    }
  ],
  "coverage": {
    "returned": 2,
    "total": 14,
    "as_of": "2026-09-24T00:00:00Z",
    "scope_note": null
  },
  "deltas": [],
  "resources": [],
  "next_actions": []
}

LLM Agent Workflow

Claude & Cursor Integration

Step 1

Prompt Trigger

"Snapshot the live Google SERP for 'claude code mcp setup' and check if there is an AI Overview."

Step 2

Agent Decision & Reasoning

The agent inspects live search results to verify ranking changes, presence of featured snippets, or displacement by AI Overviews in real time.

Step 3

Recommended Follow-up Tools

discover_ai_citations →

Provenance Guarantees & Error Handling

Reliability

Source Classlive_serp

Inspection Methodgoogle_serp

OFE Calibration Score0.85 (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 $0.002 per call of market data, so Pro's included $4 covers roughly 2000 calls. Self-hosted, it uses your own DataForSEO key and bills you directly, with nothing added. See pricing for what each tool costs.

Self-host on GitHub (MIT)Try on Cloud plan