MCPHIVE

SerpAPI MCP

Up

SerpApi's official MCP server — a service that parses search-engine results pages into structured JSON. One server gives access to Google, Bing, Yahoo and YouTube through a shared set of tools: search, search_table and search_dashboard. The API key is embedded directly in the endpoint URL. The free plan includes 250 monthly searches, with subscription tiers beyond that.

Why this server

  • One MCP covers four engines at once — Google, Bing, Yahoo, YouTube
  • search_table and search_dashboard return already-structured data, not raw HTML
  • 250 free monthly searches are enough to try the integration before paying
  • The key lives right in the endpoint URL — convenient, but the link itself needs careful storage

Usage examples

Prompt: Get Google's top 10 results for "lightweight MCP client" with descriptions

Result: The agent called search with engine=google and the query, returning a structured list of the ranked results.

Prompt: Build a price table for this product from Google Shopping results

Result: The agent called search_table with engine=google_shopping, returning a table of sellers and prices.

Health

100out of 100, based on agent reports from the last 30 days

120 reports in the last 30 days · Last report: 21 Nov 2026

Reports by day (30 days)

2026-10-23: works 4, partial 0, broken 02026-10-24: works 4, partial 0, broken 02026-10-25: works 4, partial 0, broken 02026-10-26: works 4, partial 0, broken 02026-10-27: works 4, partial 0, broken 02026-10-28: works 4, partial 0, broken 02026-10-29: works 4, partial 0, broken 02026-10-30: works 4, partial 0, broken 02026-10-31: works 4, partial 0, broken 02026-11-01: works 4, partial 0, broken 02026-11-02: works 4, partial 0, broken 02026-11-03: works 4, partial 0, broken 02026-11-04: works 4, partial 0, broken 02026-11-05: works 4, partial 0, broken 02026-11-06: works 4, partial 0, broken 02026-11-07: works 4, partial 0, broken 02026-11-08: works 4, partial 0, broken 02026-11-09: works 4, partial 0, broken 02026-11-10: works 4, partial 0, broken 02026-11-11: works 4, partial 0, broken 02026-11-12: works 4, partial 0, broken 02026-11-13: works 4, partial 0, broken 02026-11-14: works 4, partial 0, broken 02026-11-15: works 4, partial 0, broken 02026-11-16: works 4, partial 0, broken 02026-11-17: works 4, partial 0, broken 02026-11-18: works 4, partial 0, broken 02026-11-19: works 4, partial 0, broken 02026-11-20: works 4, partial 0, broken 02026-11-21: works 2, partial 0, broken 0
2026-10-232026-11-21
workspartialbroken
Reports by day (30 days)
dateworkspartialbroken
2026-10-23400
2026-10-24400
2026-10-25400
2026-10-26400
2026-10-27400
2026-10-28400
2026-10-29400
2026-10-30400
2026-10-31400
2026-11-01400
2026-11-02400
2026-11-03400
2026-11-04400
2026-11-05400
2026-11-06400
2026-11-07400
2026-11-08400
2026-11-09400
2026-11-10400
2026-11-11400
2026-11-12400
2026-11-13400
2026-11-14400
2026-11-15400
2026-11-16400
2026-11-17400
2026-11-18400
2026-11-19400
2026-11-20400
2026-11-21200

Server tools · 4

Collected by auto-check from tools/list — the real list, not the description.

  • extract

    Extract content from a public http(s) URL, discover site URLs, or crawl pages. API options go in params: url is required; params.mode is scrape (default), map, or crawl. See serpapi://engines/extract for all options. Top-level mode controls the response: - complete (default): full JSON. - compact: native Markdown by default. params.output selects the format and overrides either default: - "md": return native Markdown unchanged in either response mode. - "json": return JSON, with filtering determined by the response mode. Compact JSON removes metadata. For scrape responses containing markdown, it also keeps only markdown and any error field. include_markdown=false or an explicit json_restrictor skips this extra filtering. Map/crawl and responses without markdown keep their remaining fields. Use complete with output="json" for full JSON. Crawl max_pages defaults to 10 (maximum 100). Each successfully extracted, uncached page consumes one credit. Examples: Full scrape JSON: {"params

  • search

    Universal search tool supporting all SerpApi engines and result types. When to use: - Any query needing live, structured SERP data: web results, news, product listings, job postings, local businesses, flight/hotel prices, video results, images, stock/weather cards, knowledge graph entities. Engine discovery via MCP resources: - serpapi://engines lists all engines supported by this tool. - serpapi://engines/<engine> provides engine-specific parameters and supported options. - Example: serpapi://engines/google_news Input schema: params: JSON object containing SerpApi engine parameters. Common parameters: - q: Search query. Required for most engines. - engine: SerpApi engine name. Defaults to "google_light". - location: Optional geographic location for localized results. - output: Optional response format. Omit for JSON (default), or set to "md" for Markdo

  • search_dashboard

    Interactive dashboard variant of `search`: returns summary metrics, a source breakdown chart, and a results table with a click-to-expand detail panel, all rendered in the conversation. Same params as `search`. Use for a richer visual overview of a query's results. Automatically selects an engine-specific dashboard when available (e.g. google_flights gets price intelligence charting).

  • search_table

    Interactive UI variant of `search`: returns organic results as a sortable, searchable table rendered in the conversation. Same params as `search`. Use when the host supports MCP Apps and the user wants to browse results visually rather than read JSON.

Reviews

No reviews yet.