CoreFreeFirst-Party Ground TruthActive in MCP

Describe Capabilities

describe_capabilities()

Enabled domains, tools, fact types, source classes.

Lists enabled domains, registered tool manifests, emitted fact types, and default location/language settings.

Input Parameters

0 arguments

This tool takes no arguments.

{}

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 enabled domains, registered tool manifests, emitted fact types, and default location/language settings.

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.

Request & Response Examples

Live MCP Payloads

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

1. Client Tool Invocation

describe_capabilities request.json
{
  "tool": "describe_capabilities",
  "arguments": {}
}

2. Server Envelope Response

describe_capabilities response.json
{
  "schema_version": "ofe/1.0",
  "domain": "core",
  "data": {
    "domains": [
      "ai_visibility",
      "analytics",
      "backlinks",
      "core",
      "gsc",
      "seo",
      "serp"
    ],
    "tools": [
      {
        "name": "describe_capabilities",
        "domain": "core",
        "billing": "free",
        "implemented": true,
        "enabled": true
      },
      {
        "name": "inspect_domain",
        "domain": "seo",
        "billing": "dataforseo",
        "implemented": true,
        "enabled": true
      },
      {
        "name": "get_search_performance",
        "domain": "gsc",
        "billing": "free",
        "implemented": true,
        "enabled": true
      }
    ],
    "fact_types": [
      "ai_visibility.brand_mentions",
      "ai_visibility.citation_source",
      "analytics.traffic_summary",
      "backlinks.backlink",
      "backlinks.domain_authority",
      "gsc.index_status",
      "gsc.performance_summary",
      "seo.domain_summary",
      "seo.keyword_ranking",
      "serp.result"
    ],
    "defaults": {
      "location": "United States",
      "language": "English"
    }
  },
  "facts": [],
  "entities": [],
  "coverage": {
    "returned": 20,
    "total": 20,
    "as_of": null,
    "scope_note": null
  },
  "deltas": [],
  "resources": [],
  "next_actions": []
}

LLM Agent Workflow

Claude & Cursor Integration
Step 1

Prompt Trigger

"What SEO and search capabilities does this server have?"
Step 2

Agent Decision & Reasoning

The model runs describe_capabilities on startup or session init to discover which domains are enabled and whether DataForSEO or Google OAuth credentials are present.

Step 3

Recommended Follow-up Tools

list_websites →inspect_domain →

Provenance Guarantees & Error Handling

Reliability
Source Classcore
Inspection Methodcore.describe_capabilities
OFE Calibration Score1.00 (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

Free on every plan: it reads your own Google data, so there's no per-call cost. Works the same when self-hosted.

More Core Tools

2 sibling tools
Export DatasetFree
export_dataset()

Fetch a full dataset by mcpseo:// uri.

List WebsitesFree
list_websites()

List tracked websites and their connection state.

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