Zenserp MCP by usefulapi

Server Details

Search Google, images, news, maps, shopping, YouTube, jobs, hotels, flights and trends with Zenserp.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.

Status: Healthy
Last Tested: 2026-10-12 12:05
Transport: Streamable HTTP · MCP 2025-06-18
URL
Repository: m190/usefulapi-mcp
GitHub Stars: 0

TDQS

Score is being calculated.

Available Tools

19 tools

zenserp_answer_engineAsk an AI answer engine

Destructive

Inspect

Send a prompt to an AI answer engine (ChatGPT, Perplexity, Gemini or Copilot) and get its answer_text with citations; with brand it also reports whether and where that brand was cited. SPENDS quota at Zenserp's premium per-answer rate (see Zenserp pricing), is slow (seconds to a minute), and must not be repeated needlessly. Plan gate: Medium unlocks ChatGPT, Large adds Perplexity, Premium adds Gemini, Enterprise adds Copilot. GET /v1/answer-engine.

ParametersJSON Schema

Name	Required	Description
`brand`	No	A brand name to track: the reply then has a brand_visibility object.
`engine`	Yes	The answer engine to ask.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`prompt`	Yes	The question or prompt. prompt and additional_prompt together may hold at most 4,096 characters.
`country`	No	Two-letter country code to localise the answer, e.g. us.
`additional_prompt`	No	An optional follow-up prompt sent with the main one (counts toward the 4,096-character limit shared with prompt).

zenserp_flightsSearch Google Flights

Destructive

Inspect

Google Flights options. Best: origin and destination as 3-letter airport codes plus departure_date (dates and curr are honoured only then). A free-text q or a tfs string from a Google Flights URL also works. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v1/flights.

ParametersJSON Schema

Name	Required	Description
`q`	No	Free-text flight query, used when no airport codes are given (no dates, no curr).
`tfs`	No	Google Flights search string copied from a Google Flights URL (full filters).
`curr`	No	3-letter currency code for the prices, e.g. USD.
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`origin`	No	Departure airport code, e.g. JFK. Name one airport, not a city.
`destination`	No	Arrival airport code, e.g. LHR.
`return_date`	No	Return date, yyyy-mm-dd. Omit for one-way.
`departure_date`	No	Departure date, yyyy-mm-dd. Needs origin and destination.

zenserp_get_statusGet remaining requests

Read-only

Inspect

The number of search requests left on this Zenserp key's plan (remaining_requests). Free: it spends no quota. GET /v2/status.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

zenserp_hotelsSearch Google Hotels

Destructive

Inspect

Google Hotels offers for a hotel or place. Send check_in and check_out together, or Google falls back to today's rates. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v1/hotels.

ParametersJSON Schema

Name	Required	Description
`q`	Yes	Hotel name or place, e.g. 'hilton midtown new york'.
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`adults`	No	Number of adults.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`check_in`	No	Check-in date, yyyy-mm-dd. Needs check_out.
`children`	No	Ages of the children, comma separated, e.g. 4,9 (Google prices by age).
`currency`	No	3-letter currency code for the prices, e.g. EUR.
`check_out`	No	Check-out date, yyyy-mm-dd; later than check_in.
`free_cancellation`	No	true = only properties with free cancellation.
`accommodation_type`	No	Restrict to hotels or vacation rentals.

zenserp_image_searchSearch Google Images

Destructive

Inspect

Google image results (thumbnails, source pages, sizes). SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. Each page holds 100 images. GET /v2/search (tbm=isch).

ParametersJSON Schema

Name	Required	Description
`q`	Yes	The query.
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`lr`	No	Limit results to these languages (lr), prefixed with lang_ and joined by \|, e.g. lang_fr.
`ijn`	No	Image page number, 100 images per page; per the docs, images 101-200 = ijn 2. Omit for the first page.
`tbs`	No	Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week).
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`start`	No	Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query.
`device`	No	Device to emulate.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`location`	No	Geolocation of the search, in Google's canonical form, e.g. 'Manhattan,New York,United States' (see zenserp_search_locations). Set it when the result depends on place, especially ads.

zenserp_jobs_searchSearch Google Jobs

Destructive

Inspect

Google Jobs listings for a query (jobs_results: title, company, location, source, apply url). Google returns one page; there is no paging. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v2/search (ibp=htl;jobs).

ParametersJSON Schema

Name	Required	Description
`q`	Yes	The job query, e.g. 'php developer'.
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`location`	No	Geolocation of the search, in Google's canonical form, e.g. 'Manhattan,New York,United States' (see zenserp_search_locations). Set it when the result depends on place, especially ads.

zenserp_list_countriesList countries (gl)

Read-only

Inspect

The supported country codes (values for gl). GET /v2/gl.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

zenserp_list_languagesList languages (hl)

Read-only

Inspect

The supported interface language codes (values for hl). GET /v2/hl.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

zenserp_list_search_enginesList search engines

Read-only

Inspect

The search engine hosts Zenserp supports (values for search_engine). GET /v2/search_engines. The docs do not say whether helper lists are charged; they are not searches.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

zenserp_maps_searchSearch Google local and maps

Destructive

Inspect

Google local/maps results: shops, cafes and other businesses with address, rating, phone and coordinates. Set location for accurate results. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v2/search (tbm=lcl).

ParametersJSON Schema

Name	Required	Description
`q`	Yes	The query.
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`lr`	No	Limit results to these languages (lr), prefixed with lang_ and joined by \|, e.g. lang_fr.
`tbs`	No	Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week).
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`start`	No	Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query.
`device`	No	Device to emulate.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`location`	No	Geolocation of the search, in Google's canonical form, e.g. 'Manhattan,New York,United States' (see zenserp_search_locations). Set it when the result depends on place, especially ads.

zenserp_news_searchSearch Google News

Destructive

Inspect

Google News results for a query: title, source, date, snippet. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v2/search (tbm=nws).

ParametersJSON Schema

Name	Required	Description
`q`	Yes	The query.
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`lr`	No	Limit results to these languages (lr), prefixed with lang_ and joined by \|, e.g. lang_fr.
`tbs`	No	Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week).
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`start`	No	Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query.
`device`	No	Device to emulate.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`location`	No	Geolocation of the search, in Google's canonical form, e.g. 'Manhattan,New York,United States' (see zenserp_search_locations). Set it when the result depends on place, especially ads.

zenserp_reverse_image_searchReverse image search

Destructive

Inspect

Pages and sources that contain a given image (Google reverse image search). SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v2/search (image_url).

ParametersJSON Schema

Name	Required	Description
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`image_url`	Yes	Public URL of the image.

zenserp_searchSearch the web (SERP)

Destructive

Inspect

Live search-engine result page as JSON: organic results, ads (paid_results), featured snippets, related questions and searches, knowledge graph. Google by default; set search_engine for Bing, Yandex or DuckDuckGo. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. ai_overview=true also returns Google's AI Overview and costs 3 requests when one is returned (Small plan or higher). GET /v2/search.

ParametersJSON Schema

Name	Required	Description
`q`	Yes	The query; search operators such as site: and intitle: work.
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`lr`	No	Limit results to these languages (lr), prefixed with lang_ and joined by \|, e.g. lang_fr.
`tbs`	No	Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week).
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`start`	No	Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query.
`device`	No	Device to emulate.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`location`	No	Geolocation of the search, in Google's canonical form, e.g. 'Manhattan,New York,United States' (see zenserp_search_locations). Set it when the result depends on place, especially ads.
`ai_overview`	No	true = also extract Google's AI Overview (3 requests when returned, otherwise 1; slower; Google only; Small plan or higher).
`search_engine`	No	Search engine host, e.g. google.com (default), google.de, bing.com, yandex.com, duckduckgo.com. zenserp_list_search_engines lists them.

zenserp_search_locationsSearch geo locations

Read-only

Inspect

The supported geo locations (values for location), as Google's canonical names. The list is long: pass query to keep only entries that contain it, and limit to cap the count. GET /v2/locations.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	Most entries returned (default 50).
`query`	No	Keep only entries whose text contains this (case-insensitive), e.g. 'vienna'.

zenserp_shopping_productGet Google Shopping product page

Destructive

Inspect

Product page data from Google Shopping: description, merchant offers, variations. product_id comes from zenserp_shopping_search. With gpc_id (from the same result) it returns the whole product cluster across merchants. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v1/shopping.

ParametersJSON Schema

Name	Required	Description
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`gpc_id`	No	The Google Product Cluster id from the same search result (only valid together with its product_id).
`location`	No	Geolocation of the search, in Google's canonical form, e.g. 'Manhattan,New York,United States' (see zenserp_search_locations). Set it when the result depends on place, especially ads.
`product_id`	Yes	The product id (PID) from a Google Shopping search result.

zenserp_shopping_searchSearch Google Shopping

Destructive

Inspect

Google Shopping listings for a query: product, price, merchant, rating, and the product_id for zenserp_shopping_product. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v2/search (tbm=shop).

ParametersJSON Schema

Name	Required	Description
`q`	Yes	The query.
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`lr`	No	Limit results to these languages (lr), prefixed with lang_ and joined by \|, e.g. lang_fr.
`tbs`	No	Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week).
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`start`	No	Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query.
`device`	No	Device to emulate.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`location`	No	Geolocation of the search, in Google's canonical form, e.g. 'Manhattan,New York,United States' (see zenserp_search_locations). Set it when the result depends on place, especially ads.

zenserp_trendsGet Google Trends

Destructive

Inspect

Trending searches from Google Trends for a country, optionally narrowed to given keywords or a category. Trending data covers at most the past 7 days. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v1/trends.

ParametersJSON Schema

Name	Required	Description
`cat`	No	Google Trends category id, e.g. 16 News, 7 Finance, 18 Shopping, 20 Sports, 5 Computers & Electronics, 45 Health.
`geo`	No	Country code, e.g. US.
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`keyword`	No	Only trends matching these terms (and their related queries). A term that is not trending returns no rows.
`timeframe`	No	Window; longer ones all return the same 7-day window for trending searches.

zenserp_video_searchSearch Google Videos

Destructive

Inspect

Google video results for a query (title, channel, length, link). SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v2/search (tbm=vid).

ParametersJSON Schema

Name	Required	Description
`q`	Yes	The query.
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`lr`	No	Limit results to these languages (lr), prefixed with lang_ and joined by \|, e.g. lang_fr.
`tbs`	No	Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week).
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`start`	No	Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query.
`device`	No	Device to emulate.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`location`	No	Geolocation of the search, in Google's canonical form, e.g. 'Manhattan,New York,United States' (see zenserp_search_locations). Set it when the result depends on place, especially ads.

zenserp_youtube_searchSearch YouTube

Destructive

Inspect

YouTube search results (videos, channels, ads) for a query, optionally by location. SPENDS 1 request of the monthly quota per successful call (failed calls are not charged); do not repeat a call needlessly. GET /v2/search (search_engine=youtube.com).

ParametersJSON Schema

Name	Required	Description
`q`	Yes	The query.
`gl`	No	Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States.
`hl`	No	Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes.
`sp`	No	YouTube 'sp' filter or pagination token, as used on youtube.com.
`cache`	No	true = serve a stored copy when one exists (kept 24 h, NOT charged) and store the reply when not. Default false: every call is fetched live and charged.
`fields`	No	Only return these top-level keys of the reply (for example organic, paid_results, related_searches). Saves context; the call is charged the same.
`location`	No	Geolocation of the search, in Google's canonical form, e.g. 'Manhattan,New York,United States' (see zenserp_search_locations). Set it when the result depends on place, especially ads.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

19 tool updatesOct 12, 2026
- First observedzenserp_answer_engine
- First observedzenserp_flights
- First observedzenserp_get_status
- First observedzenserp_hotels
- First observedzenserp_image_search
- First observedzenserp_jobs_search
- First observedzenserp_list_countries
- First observedzenserp_list_languages
- First observedzenserp_list_search_engines
- First observedzenserp_maps_search
- First observedzenserp_news_search
- First observedzenserp_reverse_image_search
- First observedzenserp_search
- First observedzenserp_search_locations
- First observedzenserp_shopping_product
- First observedzenserp_shopping_search
- First observedzenserp_trends
- First observedzenserp_video_search
- First observedzenserp_youtube_search

Related MCP Connectors

Litescrape A
com.litescrape
Google, Bing, DuckDuckGo and Google Maps search results, free without an API key.
Search Browser Automation
101
Google Search Remote MCP Server A
com.hasdata
Google SERP as JSON: organic, AI Overview, People Also Ask, AI Mode, news, shopping. No Cloud setup.
Browser Automation Search Web Scraping
10118
Searlo
tech.searlo
Google SERP, Maps, Shopping, News and AI-answer data for AI agents, from the Searlo search API.
Search Location Services E-commerce & Retail
1
google-search
com.mcparmory
Scrape Google search results with SERP data, ads, and knowledge panels
Web Scraping Search
3

Related MCP Servers

OpenSERP Cloudofficial
Search Browser Automation Web Scraping
openserpapi
A
license
B
quality
C
maintenance
Search API for AI, SEO & automation. Browser-rendered Google, Bing, Yandex, Baidu, DuckDuckGo and Ecosia results with URL extraction (+image search and engine metadata tools)
Updated 6 days ago (2026-10-06 19:53 UTC)
9
113 npm
2
MIT
Google Cheap Search
Search Web Scraping
SerpCheap
A
license
A
quality
D
maintenance
Provides real-time Google search results (organic + knowledge graph) with country targeting, language, time filters, and pagination, at low cost.
Updated 4 months ago (2026-06-10 05:53 UTC)
1
12 npm
MIT
SERPJET MCP Server
Search Web Scraping
jibaoproxyofficial-pixel
A
license
A
quality
D
maintenance
Enables AI agents to perform Google searches and retrieve structured JSON results for 10 types including web, images, news, and shopping with live prices. Offers 1,000 free searches per month with no credit card required.
Updated 3 months ago (2026-07-10 12:30 UTC)
1
26 npm
MIT
Talordata MCP Server
Developer Tools RAG Systems Web Scraping
hanxing95
A
license
Not graded
quality
D
maintenance
Search Google and major search engines through Talordata SERP API for AI agents and RAG workflows.
Updated 4 months ago (2026-06-05 07:39 UTC)
MIT