MCP server for advanced web search using Tavily
Nothing to run from here
Zenserp MCP by usefulapi is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
19
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Search Google, images, news, maps, shopping, YouTube, jobs, hotels, flights and trends with Zenserp.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http zenserp-mcp-by-usefulapi https://zenserp.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# zenserp_get_status, zenserp_search, zenserp_image_search and 16 more
Zenserp MCP by usefulapi costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
USAll 334 servers
usefulapi334 servers
24 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http zenserp-mcp-by-usefulapi https://zenserp.usefulapi.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
19 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
The number of search requests left on this Zenserp key's plan (remaining_requests). Free: it spends no quota. GET /v2/status.
No parameter schema on file.
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | The query; search operators such as site: and intitle: work. |
| search_engine | string | no | Search engine host, e.g. google.com (default), google.de, bing.com, yandex.com, duckduckgo.com. zenserp_list_search_engines lists them. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| lr | string | no | Limit results to these languages (lr), prefixed with lang_ and joined by |, e.g. lang_fr. |
| location | string | 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. |
| device | string | no | Device to emulate. |
| start | integer | no | Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query. |
| tbs | string | no | Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week). |
| ai_overview | boolean | no | true = also extract Google's AI Overview (3 requests when returned, otherwise 1; slower; Google only; Small plan or higher). |
| cache | boolean | 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 | array | 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. |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | The query. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| lr | string | no | Limit results to these languages (lr), prefixed with lang_ and joined by |, e.g. lang_fr. |
| location | string | 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. |
| device | string | no | Device to emulate. |
| start | integer | no | Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query. |
| tbs | string | no | Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week). |
| ijn | integer | no | Image page number, 100 images per page; per the docs, images 101-200 = ijn 2. Omit for the first page. |
| cache | boolean | 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 | array | 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. |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | The query. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| lr | string | no | Limit results to these languages (lr), prefixed with lang_ and joined by |, e.g. lang_fr. |
| location | string | 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. |
| device | string | no | Device to emulate. |
| start | integer | no | Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query. |
| tbs | string | no | Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week). |
| cache | boolean | 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 | array | 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. |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | The query. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| lr | string | no | Limit results to these languages (lr), prefixed with lang_ and joined by |, e.g. lang_fr. |
| location | string | 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. |
| device | string | no | Device to emulate. |
| start | integer | no | Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query. |
| tbs | string | no | Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week). |
| cache | boolean | 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 | array | 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. |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | The query. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| lr | string | no | Limit results to these languages (lr), prefixed with lang_ and joined by |, e.g. lang_fr. |
| location | string | 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. |
| device | string | no | Device to emulate. |
| start | integer | no | Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query. |
| tbs | string | no | Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week). |
| cache | boolean | 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 | array | 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. |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | The query. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| lr | string | no | Limit results to these languages (lr), prefixed with lang_ and joined by |, e.g. lang_fr. |
| location | string | 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. |
| device | string | no | Device to emulate. |
| start | integer | no | Result offset: 0 (default) first page, 10 second page, 20 third page ... Google serves about 300 results per query. |
| tbs | string | no | Google 'tbs' filter string for what the query field cannot express, e.g. qdr:w (past week). |
| cache | boolean | 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 | array | 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. |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | The query. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| location | string | 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. |
| sp | string | no | YouTube 'sp' filter or pagination token, as used on youtube.com. |
| cache | boolean | 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 | array | 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. |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| image_url | string | yes | Public URL of the image. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| cache | boolean | 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 | array | 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. |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | The job query, e.g. 'php developer'. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| location | string | 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. |
| cache | boolean | 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 | array | 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. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| product_id | string | yes | The product id (PID) from a Google Shopping search result. |
| gpc_id | string | no | The Google Product Cluster id from the same search result (only valid together with its product_id). |
| location | string | 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. |
| cache | boolean | 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 | array | 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. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Hotel name or place, e.g. 'hilton midtown new york'. |
| check_in | string | no | Check-in date, yyyy-mm-dd. Needs check_out. |
| check_out | string | no | Check-out date, yyyy-mm-dd; later than check_in. |
| adults | integer | no | Number of adults. |
| children | string | no | Ages of the children, comma separated, e.g. 4,9 (Google prices by age). |
| currency | string | no | 3-letter currency code for the prices, e.g. EUR. |
| accommodation_type | string | no | Restrict to hotels or vacation rentals. |
| free_cancellation | boolean | no | true = only properties with free cancellation. |
| hl | string | no | Interface language (hl), e.g. en, de, pt-BR. zenserp_list_languages lists the supported codes. |
| gl | string | no | Country (gl), two letters, e.g. us, de, gb. zenserp_list_countries lists the supported codes. Default: United States. |
| cache | boolean | 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 | array | 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. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| origin | string | no | Departure airport code, e.g. JFK. Name one airport, not a city. |
| destination | string | no | Arrival airport code, e.g. LHR. |
| departure_date | string | no | Departure date, yyyy-mm-dd. Needs origin and destination. |
| return_date | string | no | Return date, yyyy-mm-dd. Omit for one-way. |
| curr | string | no | 3-letter currency code for the prices, e.g. USD. |
| q | string | no | Free-text flight query, used when no airport codes are given (no dates, no curr). |
| tfs | string | no | Google Flights search string copied from a Google Flights URL (full filters). |
| cache | boolean | 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 | array | 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. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| geo | string | no | Country code, e.g. US. |
| keyword | array | no | Only trends matching these terms (and their related queries). A term that is not trending returns no rows. |
| cat | integer | no | Google Trends category id, e.g. 16 News, 7 Finance, 18 Shopping, 20 Sports, 5 Computers & Electronics, 45 Health. |
| timeframe | string | no | Window; longer ones all return the same 7-day window for trending searches. |
| cache | boolean | 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 | array | 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. |
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 Gem
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | The answer engine to ask. |
| prompt | string | yes | The question or prompt. prompt and additional_prompt together may hold at most 4,096 characters. |
| additional_prompt | string | no | An optional follow-up prompt sent with the main one (counts toward the 4,096-character limit shared with prompt). |
| country | string | no | Two-letter country code to localise the answer, e.g. us. |
| brand | string | no | A brand name to track: the reply then has a brand_visibility object. |
| fields | array | 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. |
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.
No parameter schema on file.
The supported interface language codes (values for hl). GET /v2/hl.
No parameter schema on file.
The supported country codes (values for gl). GET /v2/gl.
No parameter schema on file.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Keep only entries whose text contains this (case-insensitive), e.g. 'vienna'. |
| limit | integer | no | Most entries returned (default 50). |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Zenserp MCP by usefulapi or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Zenserp MCP by usefulapi can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.