SEOPro / BYOKSearch IndexActive in MCP

Inspect Keyword

inspect_keyword(keyword: string)

Search volume, difficulty, CPC and intent for one keyword.

How big and how hard one keyword is: monthly search volume, CPC, paid competition, organic difficulty and search intent, from the search index. It doesn't fetch Google's live results; inspect_serp does that, so the two never disagree about who ranks.

Input Parameters

1 argument

Parameter	Type	Requirement	Default / Constraints	Description
`keyword`	`string`	required	none	The keyword to inspect.

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

`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
`seo.keyword_opportunity`	Demand and difficulty for the keyword, in the same shape research_keywords returns.	`keywordsearch_volumecpccompetitionkeyword_difficultysearch_intent`

Registered Entities

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

keyword

The keyword inspected.

Request & Response Examples

Live MCP Payloads

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

1. Client Tool Invocationinspect_keyword request.json
{
  "tool": "inspect_keyword",
  "arguments": {
    "keyword": "open source mcp server"
  }
}

2. Server Envelope Responseinspect_keyword response.json
{
  "schema_version": "ofe/1.0",
  "domain": "seo",
  "data": {
    "keyword": "open source mcp server",
    "search_volume": 2400,
    "cpc": 1.85,
    "competition": 0.28,
    "keyword_difficulty": 24,
    "search_intent": "informational"
  },
  "facts": [
    {
      "type": "seo.keyword_opportunity",
      "subject": [
        "keyword:en:US:open source mcp server"
      ],
      "data": {
        "keyword": "open source mcp server",
        "search_volume": 2400,
        "cpc": 1.85,
        "competition": 0.28,
        "keyword_difficulty": 24,
        "search_intent": "informational"
      },
      "provenance": {
        "source_class": "search_index",
        "method": "keyword_overview",
        "confidence": 0.75,
        "observed_at": "2026-09-24T00:00:00Z",
        "cache_hit": false
      }
    }
  ],
  "entities": [
    {
      "id": "keyword:en:US:open source mcp server",
      "kind": "keyword",
      "label": "open source mcp server"
    }
  ],
  "coverage": {
    "returned": 1,
    "total": 1,
    "as_of": "2026-09-24T00:00:00Z",
    "scope_note": null
  },
  "deltas": [],
  "resources": [],
  "next_actions": [
    {
      "tool": "inspect_serp",
      "args": {
        "keyword": "open source mcp server"
      },
      "use_when": "to see who ranks for it on Google right now"
    }
  ]
}

LLM Agent Workflow

Claude & Cursor Integration

Step 1

Prompt Trigger

"Is 'open source mcp server' worth targeting, and who ranks #1?"

Step 2

Agent Decision & Reasoning

The agent checks volume, difficulty and intent with inspect_keyword, then calls inspect_serp for the live results page.

Step 3

Recommended Follow-up Tools

inspect_serp →research_keywords →

Provenance Guarantees & Error Handling

Reliability

Source Classsearch_index

Inspection Methodkeyword_overview

OFE Calibration Score0.75 (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 $0.014 per call of market data, so Pro's included $4 covers roughly 285 calls. Self-hosted, it uses your own DataForSEO key and bills you directly, with nothing added. See pricing for what each tool costs.