MCP: SEO Keyword & Search-Demand Intel

An MCP server wrapping keyword-demand-intel so AI agents can pull keyword and search-demand intelligence as native tool calls. x402 (USDC on Base) and Skyfire agentic-payment ready.

Tools

Tool	What it does
expand_keywords	Expand a seed into its long-tail universe via Google autosuggest, with intent + estimated volume + proxy difficulty per keyword.
keyword_metrics	The full bundle for a seed: expansion + volume + difficulty + live SERP features + topic clusters (and optional Trends seasonality).
analyze_serp	Fetch the logged-out Google SERP for one query: top results, SERP features, People-Also-Ask, related searches, and difficulty.
keyword_difficulty	Score ranking difficulty (0-100) for a keyword from its live SERP - authority domains, ads, and featured-snippet pressure.
trend_signal	A Google Trends seasonality signal for a keyword (rising / falling / flat / seasonal, peak month, spikiness). Best-effort.

Modes

• list_tools - emit the tool catalog (name, description, JSON input schema) plus the agentic-payment descriptor. Free.
• call_tool - invoke one tool. Requires tool + args.
• batch - invoke up to 10 {tool, args} calls in one run.

{ "mode": "call_tool", "tool": "expand_keywords", "args": { "seed": "crm software", "country": "US", "limit": 80 } }

How it works

Each tool calls the upstream seibs.co/keyword-demand-intel actor via Actor.call(), reads its dataset, and reshapes the records into compact, deterministic JSON ({ tool, args, ok, count, items, summary, error }). Tools never throw - upstream failure or a blocked SERP becomes ok: false with a documented error.

Connect it to an MCP client

This Actor is exposed as a remote MCP tool through Apify's hosted MCP server. Point any MCP-compatible client (Claude Desktop, Cursor, VS Code, or an OpenAI / LangChain / LlamaIndex agent) at Apify's server with this Actor enabled:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=seibs.co/mcp-keyword-demand-intel",
      "headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" }
    }
  }
}

Get a token (free) from Apify Console -> Settings -> API & Integrations. The Actor then appears as a callable tool. Run mode=list_tools first (free) to fetch every tool's live JSON schema, then call one:

{ "mode": "call_tool", "tool": "expand_keywords", "args": { } }

Prefer a direct call? Hit the Actor straight through the Apify API / SDK - no MCP client required:

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("seibs.co/mcp-keyword-demand-intel").call(run_input={
    "mode": "call_tool", "tool": "expand_keywords", "args": {},
})
items = client.dataset(run["defaultDatasetId"]).list_items().items

Pricing

Flat $0.005 per MCP tool call (mcp_tool_call). The upstream actor charges its own pay-per-event events (keyword_record $0.003, volume_estimate $0.006, serp_snapshot $0.008) directly to the same run as pass-through, so total cost = $0.005 per call + upstream usage. x402 / Skyfire enable token-less per-call payment for direct AI agents when MCP monetization is enabled.

Posture

Logged-out public Google surfaces only (autosuggest, the public SERP, public Trends), rate-limited, no PII. Volume and difficulty are clearly-labeled estimates from a published model, not Google's gated Keyword Planner figures. See the main actor for the full source and legal-safety notes.