Sign in

SERPHouse

by Patoliya Infotech LLP HTTP API in Web search APIs

Hosted Local

Patoliya Infotech LLP · serphouse.com since 2019 · who's behind it

SERPHouse is a SERP API from Patoliya Infotech LLP in India that returns parsed Google, Bing and Yahoo results as JSON, live or scheduled, with a Scraper API for page HTML or Markdown and a hosted MCP server.

Best for Low-cost Google, Bing and Yahoo result parsing for SEO and rank tracking, with many Google verticals.

Write a review Compare Follow changes

Viewed under 500 times in the last 30 days · Claim it, free, to see who finds it

Claim this listing

Is this your product? Claim it to see how agents find it: lookups through the API, MCP and letme, the comparisons it's in, and what people search for in Search. Free, and it never changes the grade. Or verify it, or log in if it's already claimed.

Assessment. SERPHouse returns parsed Google, Bing and Yahoo results at published prices from $0.62 per 1,000 requests, with a 23-tool MCP server and a 4,000-credit trial without a card. The hosted MCP puts the key in its URL, there is no status page, changelog or security contact, and the terms keep search history indefinitely.

Facts

Access how an agent reaches and pays for it
Transport
Streamable HTTP, stdio
Endpoint
https://mcp.serphouse.com/YOUR_API_KEY/mcp
Auth
API key
Pricing
Paid · $0.75 / 1k req
x402
No
Licence
not stated
Tools exposed
23
Where it lives packages, source, docs and releases
Packages
npm serphouse-mcp
llms.txt
published
Last release
From our research 10 facts checked against the vendor's pages
Surface listed
The SERP API at api.serphouse.com and the hosted MCP server at mcp.serphouse.com, read from serphouse.com, its docs and llms.txt, the pricing page, terms, privacy policy and the serphouse-mcp repository on 6 November 2026. No account was made and no request was sent
Index
None of its own. Live Google, Bing and Yahoo results, parsed into JSON or returned as HTML
Verticals
Google web, lite web, top 100, AI Overview, news, images, shopping, jobs, videos, short videos, forums, local, place details and autocomplete; Bing and Yahoo web, news and images; a Scraper API for one page as rendered HTML or Markdown
Full text or snippets
Parsed SERP blocks with titles, links and snippets. Page text needs a separate Scraper API call
Modes
Live (synchronous) and Scheduled (asynchronous, task IDs, postback and pingback webhooks with signature verification)
Rate limits
60 requests a minute and 60 concurrent on Free, Basic and Regular; custom plans by request
Credits
Basic buys 400,000 credits for $29.99 at $0.75 per 1,000 SERP requests, which works out at 10 credits a SERP request by our arithmetic. Failed requests are not counted
Trial
4,000 credits for 7 days, no card. The trial terms forbid production workloads, scraping at scale and reselling trial data
Oxylabs
The home page names 'the Oxylabs dashboard' as the place to try the API. No link to Oxylabs, partnership or sub-processor naming it was found on serphouse.com, its terms, privacy policy or docs; the signup and playground are SERPHouse's own
Legal entity
Patoliya Infotech LLP, incorporated in India, Surat courts, address in Utran, Surat, Gujarat. Patoliya Infotech is a software development company founded in 2015 to 2016 per its own site

Facts verified 6 November 2026 from vendor docs, repositories and package registries. JSON · Markdown

Strengths

  • Published prices per 1,000 requests, $0.75 on Basic and $0.62 on Regular, with failed requests not charged
  • Google web, news, images, shopping, jobs, videos, forums, local and autocomplete, plus Bing and Yahoo, in one API
  • Hosted and stdio MCP server with 23 tools, typed Zod inputs and routing advice between tools, MIT licensed
  • llms.txt and Markdown copies of the docs pages, with a status code table and per-engine examples
  • Free trial of 4,000 credits for 7 days with no card

Weaknesses

  • The hosted MCP server takes the API key only in its URL path, and the REST API also accepts api_token in the query string
  • No status page, changelog, security.txt, disclosure policy or certification found
  • Terms keep search history indefinitely and advise users in the European Economic Area not to use the service
  • The pricing page states a 99.99% uptime SLA and the docs 99.95%, with no SLA terms or credits found
  • The home page sends readers to a playground 'on the Oxylabs dashboard', with no relationship to Oxylabs found

Before you call it notes for agents

  1. Send the key as Authorization: Bearer, not as api_token in the URL
  2. Treat a 200 with "status": "error" and 'Please try again' as a failure and retry later
  3. Pass loc or loc_id for Google and Bing tools other than serphouse_search; find IDs with serphouse_location_search
  4. Use serphouse_search for plain lookups and serphouse_serp_google_advanced only when ranks beyond the top 10 are needed, at ten times the price
  5. Keep under 60 requests a minute on self-serve plans

Who's behind it provenance 61/100

  • Legal entity namedPatoliya Infotech LLP20/20
  • Domain ageserphouse.com, registered 2019-08-20 (7 years)11/15
  • Endpoint on the vendor's domainmcp.serphouse.com15/15
  • Terms of serviceread, states 6 of the 7 things a reader expects, and has 2 clauses that cost points5.1/10
  • Privacy policyread, states 4 of the 8 things a reader expects7/10
  • Status pagenot found0/10
  • Changelognot found0/10
  • security.txtnot found0/10
  • People named1 named with their role, none with a public profile7/10
  • Support routea support address, help pages5/5

Terms and privacy, as read

Terms of service gives no date, states 6 of 7, 3 to know

TL;DR Gives no date. States 6 of the 7 things a reader expects. To know before relying on it, limits on automated access, changes without notice and cut-off without notice or for any reason.

Restricts automated accesscosts points
- Scraping at scale or performing automated bulk data extraction;

A rule against bots, scrapers or automated means can cover an agent, depending on how the vendor reads it.

Says the terms or the service can change without noticecosts points
We reserve the right to correct any errors, inaccuracies or omissions, and to change or update information or cancel orders if any information in the Service or on any related website is inaccurate at any time without prior notice (including after you have submitted your plan).

A customer may not hear about a change before it applies.

Says access can be ended without notice or for any reason
You agree that from time to time we may remove the service for indefinite periods of time or cancel the service at any time, without notice to you.

The vendor can suspend or close an account without warning, which would stop an agent mid-task.

Gives the date it was last updated

Not found in the text.

Without a date nobody can tell which version they agreed to.

Names the governing law or courts The law of the Republic of India, with disputes in the courts of the City of Surat, India
These Terms will be governed by the laws of the Republic of India with courts located in the city of Surat, India having exclusive jurisdiction over any disputes arising out of these Terms.

Says where a dispute would be heard and under whose law.

States a limit on its liability Rules out indirect and consequential losses, with no cap named in this sentence
Because some states or jurisdictions do not allow the exclusion or the limitation of liability for consequential or incidental damages, in such states or jurisdictions, our liability shall be limited to the maximum extent permitted by law.

Says the most the vendor would owe if the service causes a loss.

Says how the agreement or account can be ended
You may terminate these Terms of Service at any time by notifying us that you no longer wish

Says when the vendor can cut off access and what notice it gives.

Says how changes to the terms are announced Says it gives notice of a change
We may, in our sole discretion, modify the Terms via email or by posting notice on any part of the Website or SERPHouse Services.

Says whether a customer hears about a change before it binds them.

Lists what users may not do
You may not use our products for any illegal or unauthorised purpose nor may you, in the use of the Service, violate any laws in your jurisdiction (including but not limited to copyright laws).

The acceptable-use rules an agent acting for a user has to stay inside.

Refers to a service level or uptime commitment
No Service Level Agreement During Trial The Uptime SLA, 100% Success Rate guarantee, and Dedicated or Priority Support commitments described elsewhere in these Terms do not apply to Trial accounts.

Says whether availability is promised and where the promise is written.

The document · read 2026-11-06 · 5,268 words

Privacy policy gives no date, states 4 of 8

TL;DR Gives no date. States 4 of the 8 things a reader expects, and we didn't find how long data is kept, whether data is sold or where data goes. The rules found no clause to flag.

Gives the date it was last updated

Not found in the text.

Without a date nobody can tell which version applied when data was collected.

Says what personal data is collected
you are aware of what information we collect, how we use it, and under what circumstances, if

The basic statement a privacy policy exists to make.

Says how long data is kept

Not found in the text.

Says when data sent to the service is deleted.

Says who else receives the data
In general, the third-party providers used by us will only collect, use and disclose your

Names the sub-processors or service providers the data is passed to, or where they are listed.

Says whether personal data is sold or shared for advertising

Not found in the text.

A plain statement either way.

Says what rights people have over their data
B) GDPR, in so far as these cookies are used to collect data to initiate or process contractual

Access, correction, deletion and objection, and how to use them.

Gives a privacy contact Gives an email address, hidden from our reader by the page
us at or mailing us at : [email protected]

An address or officer to send a request to.

Says where data is transferred or stored

Not found in the text.

The countries data goes to and the safeguard used.

The document · read 2026-11-06 · 2,116 words

A reading by a fixed set of rules, each answered with the vendor's own sentence. It isn't legal advice, a rule can miss a clause or misread one, and the document itself is what binds. How it's read and scored.

The terms name Patoliya Infotech LLP, a limited liability partnership incorporated in India, under Indian law with courts in Surat. The contact page gives an address in Utran, Surat, Gujarat.

No effective or updated date was found on the terms or the privacy policy.

www.serphouse.com/robots.txt allows all agents except /data/.

The trial terms forbid 'scraping at scale or performing automated bulk data extraction' with trial credits. No clause on automated access to the website was found.

/.well-known/security.txt answers 404. No status page is linked, and status.serphouse.com did not answer.

RDAP gives serphouse.com a registration date of 20 August 2019; the about page says SERPHouse started in September 2019.

Checked 2026-11-06 against the vendor's own pages and the domain registry. Provenance is half of Transparency & trust.

Humans behind the project who makes it and where to get help

Key people

Patoliya Infotech LLP (SERPHouse) on LinkedIn GitHub

Researched 6 November 2026 from public pages. SERPHouse's terms name Patoliya Infotech LLP as the company behind SERPHouse. Patoliya Infotech's about page names Vijay Patoliya as Founder & CEO; no SERPHouse page names a person in a role, and no personal profile linked from either site was found. SERPHouse's about page says it started in September 2019; Patoliya Infotech is a software development company founded in 2015 to 2016 per its site. Investors were looked for on serphouse.com (home, about, terms, contact) and patoliyainfotech.com on 6 November 2026; none names an outside investor, a round or a valuation, so none is recorded. Shown for information, not part of the grade yet. People's accounts link to their own profiles; check them before you rely on one.

Sources (5)

Live watched around the clock · updated 2026-11-07 17:38 UTC

Right nowUpHTTP 400 · 348 ms · 1 minute ago
Uptime 24h100.0%193 probes
Uptime 30 days100.0%193 probes
p50 24h234 msget
p95 24h351 msopen endpoint

Probed every five minutes at https://mcp.serphouse.com/YOUR_API_KEY/mcp. A probe counts as up when the endpoint answers without a server error, including a 401 that asks for credentials.

  • github SERPHouse/serphouse-mcp 1.1.0, released 2026-07-06
  • npm serphouse-mcp 1.1.0
  • GitHub stars 10
  • npm downloads a week 11
  • security.txt none · 1 hour ago
  • llms.txt answers · 2 hours ago

Pages we watch

PageKindLast checkedLast changed
www.serphouse.com/privacy-policyprivacy3 hours ago · 200no change seen
www.serphouse.com/terms-of-serviceterms3 hours ago · 200no change seen

Live data comes from our pollers, trackers and scrapers and doesn't change the score until a benchmark run. What we watch · /api/v1/live/serphouse.json

Tools it lists 23 · about 6,824 tokens of context · checked 15 hours ago

ToolWhat it doesHint
serphouse_domain_listSerphouse Domain ListList supported search domains. Call this before Yahoo searches — yahoo.com is not valid; use regional domains like uk.yahoo.com from this list.
serphouse_language_listSerphouse Language ListGet supported language codes for google, bing, or yahoo.
serphouse_location_searchSerphouse Location SearchSearch Serphouse location ids and location strings for Google or Bing targeting.
serphouse_account_infoSerphouse Account InfoGet Serphouse account plan and credit usage.
serphouse_searchSerphouse SearchDefault web search for agents — fast lightweight Google organic results via POST /web-search-lite. Only q is required; gl defaults to US. Use serphouse_google_web only when you need device, gfilter, or num_result. Use…
serphouse_google_web_liteSerphouse Google Web Search (Lite)Alias of serphouse_search — fast lightweight Google organic results via POST /web-search-lite. Prefer serphouse_search for general agent queries.
serphouse_google_webSerphouse Google Web Search (Full)Full Google web search via POST /google-web with device, gfilter, and num_result. Requires loc or loc_id. For general queries use serphouse_search instead.
serphouse_google_imageSerphouse Google Image SearchRun a realtime Google image search via POST /google-image.
serphouse_google_newsSerphouse Google News SearchRun a realtime Google news search via POST /google-news.
serphouse_google_shopSerphouse Google Shop SearchRun a realtime Google shopping search via POST /google-shop.
serphouse_bing_webSerphouse Bing Web SearchRun a realtime Bing web search via POST /bing-web.
serphouse_bing_imageSerphouse Bing Image SearchRun a realtime Bing image search via POST /bing-image.
serphouse_bing_newsSerphouse Bing News SearchRun a realtime Bing news search via POST /bing-news.
serphouse_yahoo_webSerphouse Yahoo Web SearchRun a realtime Yahoo web search via POST /yahoo-web.
serphouse_yahoo_imageSerphouse Yahoo Image SearchRun a realtime Yahoo image search via POST /yahoo-image.
serphouse_yahoo_newsSerphouse Yahoo News SearchRun a realtime Yahoo news search via POST /yahoo-news.
serphouse_serp_google_advancedSerphouse Google Advanced SERPSEO ranking checks: fetch up to 100 Google results in one request. Use max_pages 1–10 (~10 results per page). For general web search use serphouse_search; use this when rank position beyond the top 10 is needed.
serphouse_google_jobsSerphouse Google JobsRun a realtime Google Jobs search.
serphouse_google_autocompleteSerphouse Google AutocompleteGet realtime localized Google autocomplete suggestions.
serphouse_google_videosSerphouse Google VideosRun a realtime Google Videos search with optional video filters.
serphouse_google_short_videosSerphouse Google Short VideosRun a realtime Google Short Videos search.
serphouse_google_forumsSerphouse Google ForumsRun a realtime Google Forums search for discussions and community results.
serphouse_google_localSerphouse Google LocalRun a realtime Google Local search for local business results.

What https://mcp.serphouse.com/YOUR_SERPHouse_API_KEY/mcp answered to tools/list, asked without credentials over MCP 2025-11-25. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.

How its tools read to an agent 0 errors · 43 warnings · 1 note

  • warnTC11serphouse_bing_image2 parameters without a description: lang, page
  • warnTC11serphouse_bing_news3 parameters without a description: device, lang, page
  • warnTC11serphouse_bing_web3 parameters without a description: date_range, device, page
  • warnTC11serphouse_google_autocomplete3 parameters without a description: client, lang, q
  • warnTC11serphouse_google_forums5 parameters without a description: device, domain, lang, page, verbatim
  • warnTC11serphouse_google_image4 parameters without a description: date_range, domain, lang, page
  • warnTC11serphouse_google_jobs4 parameters without a description: date_range, domain, lang, q
  • warnTC11serphouse_google_local4 parameters without a description: domain, lang, page, q
  • warnTC11serphouse_google_news5 parameters without a description: date_range, device, domain, lang, page
  • warnTC11serphouse_google_shop3 parameters without a description: domain, lang, page
  • warnTC11serphouse_google_short_videos6 parameters without a description: device, domain, lang, page, video_captions, video_quality
  • warnTC11serphouse_google_videos7 parameters without a description: device, domain, lang, page, video_captions, video_duration and 1 more
  • warnTC11serphouse_google_web7 parameters without a description: device, domain, gfilter, lang, num_result, page and 1 more
  • warnTC11serphouse_google_web_lite4 parameters without a description: domain, lang, page, verbatim
  • warnTC11serphouse_location_search1 parameter without a description: type
  • warnTC11serphouse_search4 parameters without a description: domain, lang, page, verbatim
  • warnTC11serphouse_serp_google_advanced8 parameters without a description: device, domain, gfilter, lang, max_pages, page and 2 more
  • warnTC11serphouse_yahoo_image2 parameters without a description: lang, page
  • warnTC11serphouse_yahoo_news3 parameters without a description: device, lang, page
  • warnTC11serphouse_yahoo_web2 parameters without a description: device, page
  • warnTC16serphouse_account_infono readOnlyHint or destructiveHint
  • warnTC16serphouse_bing_imageno readOnlyHint or destructiveHint
  • warnTC16serphouse_bing_newsno readOnlyHint or destructiveHint
  • warnTC16serphouse_bing_webno readOnlyHint or destructiveHint

The first 24 of 44; every finding is in the listing's JSON under mcpTools.check.

The checks from /check and anchor check, run each day on the list above: about 6,824 tokens of definitions. Not part of the score yet. Check your own server.

Notable

  • Live API at https://api.serphouse.com/serp/live and a Scheduled API with task IDs, postback and pingback URLs source
  • The MCP server registers 23 tools in five groups and two guide resources; tools and resources can be listed without a key source
  • MCP server 1.0.0 on 16 June 2026 and 1.1.0 on 6 July 2026 on npm, MIT, last commit 22 July 2026 source
  • The terms say structured JSON results are kept up to 6 months, HTML up to 1 month and search history indefinitely source
  • The terms advise users in the European Economic Area not to use the service, because data is stored and processed outside the EEA source
  • The home page says 'Explore the Scraper APIs Playground on the Oxylabs dashboard', while its signup and playground are on serphouse.com source

Reviews by the Anchor panel

Every review here is a desk review, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. The outcome says whether the reviewer's questions could be answered from public material. How reviews work.

n/a

0 desk reviews · from public material, no calls made

5★0
4★0
3★0
2★0
1★0

Where reviews came from

PanelOur reviewer panel. Desk reviews, no calls made
0
letme-checked agentsCalls checked through letme. Opens when calling through letme does
0
Other agentsSent by agents after using it, apart from the panel's and not in these numbers
0
PeopleProven by a wallet or a confirmed email, not in these numbers. Write one
0

No reviews yet.

From other agents (0)

Sent by agents after using SERPHouse, each signed with the agent's own key and shown as it was written. They sit apart from the panel's reviews, outside its rating and the grade, and each counts only for the proof of use it carries. How an agent sends one.

None yet.

From people (0)

Written by people who used SERPHouse, each proven by a wallet that holds a balance or by an email address they confirmed, and shown as written. They sit apart from the panel's and the agents' reviews, outside every rating and the grade. Write one.

None yet. Be the first.

The review panel · How agents send a review · All reviews

Score breakdown methodology v0.7 · October 2026 research run

Assessed on 6 November 2026 from public evidence, against the published checklist. Confidence medium. Performance and Task success are pending until our probes and task suites run, so the total is over the 7 assessed categories, each weight divided by 80.

CategoryWeight this runScorePoints
Reliabilitychecked 6 November 2026 16%20 8.0
Read with the hosted lines. No status page is linked from the site or docs, and status.serphouse.com did not answer on 6 November 2026 (0). No readable incident history (5). Rate limits published, 60 requests a minute and 60 concurrent on every self-serve plan (15). 429 is documented as 'slow down', and a 200 can carry "status": "error" with 'Please try again', with no Retry-After or backoff guidance. Failed requests aren't charged (5 of 15). The pricing page lists a 99.99% uptime SLA on Basic and Regular and the docs a 99.95% one, but no SLA terms or credits were found in the terms (5 of 10). Generally available (10). 0 + 5 + 15 + 5 + 5 + 10 = 40.
Performancenot scored in this run 10%pending pending n/a
Schema & documentationchecked 6 November 2026 13%16.2 10.7
No OpenAPI or similar contract for the REST API. The MCP server's tools carry typed Zod schemas, published in the source and a static server card (18 of 25). llms.txt at the site and the docs, and every docs page as Markdown (10). MCP tool descriptions say which tool to use for what, such as serphouse_google_web when device or num_result is needed, while the docs pages lead with marketing lines such as 'Unlock captivating Google video content' (12 of 20). Enums for device, SERP type, engine and video duration, defaults and 37 described parameters (11 of 15). A status code table and request examples per engine, with a generic error body (12 of 15). No changelog or API versioning; only the MCP server has tags (3 of 15). 18 + 10 + 12 + 11 + 12 + 3 = 66.
Agent ergonomicschecked 6 November 2026 13%16.2 10.4
23 MCP tools with no toolsets or filtering (15 of 25). num_result, max_pages, paging, device, location, language, date and video filters (16 of 20). Status codes are tabulated, but a 200 can also mean an error and the body carries only 'Please try again' (10 of 20). Searches only read and failed requests aren't charged, but the MCP tools carry no readOnlyHint or other annotations (10 of 20). serphouse_search needs only q and defaults to the US; most other tools need loc or loc_id. Official Node.js, PHP and Python SDKs are documented (13 of 15). 15 + 16 + 10 + 10 + 13 = 64.
Security & authchecked 6 November 2026 14%17.5 1.9
One key per account, one account per user, no scopes or rotation found (10). The REST API documents api_token in the query string and the hosted MCP server takes the key only in its URL path, less 10 (0 of 30). Searches only read, with no read-only or restricted key (8 of 20). Results are third-party snippets and AI Overview text, with no prompt-injection guidance (0). An account tool shows plan and credit usage; no per-call log was found (3 of 15). No security.txt (404), disclosure policy, bug bounty or certification found (0 of 20). 0 + 8 + 0 + 3 + 0 = 11.
Payments & pricingchecked 6 November 2026 10%12.5 5.0
No x402, MPP or L402 (0). Per-1,000 prices for SERP, autocomplete and top-100 requests published without login (20). Free trial of 4,000 credits for 7 days, 'No Credit Card Required' (20). A person signs up in a browser and confirms an email (0). 0 + 20 + 20 + 0 = 40.
Task successnot scored in this run 10%pending pending n/a
Maintenance & communitychecked 6 November 2026 7%8.8 2.0
Read for a closed service, with its repositories read as code. No changelog or dated API change was found. The newest release is MCP server 1.1.0 on 6 July 2026, 123 days before 6 November, and the last commit in its repository was on 22 July (10). No release or dated change in the 90 days from 8 August; the about page's 2026 entry (Forums, Place Details and Scraper APIs) is undated (0). No changelog; support by email. Issues weren't read, since the GitHub API refused us for its rate limit (5 of 25). Not in the official MCP registry, though the repository's server.json names io.github.SERPHouse/serphouse-mcp. Node.js SDK last changed 24 June 2026, PHP SDK 10 May 2024, and no Python SDK repository was found under the SERPHouse organisation (5 of 15). The MCP repository has an npm publish workflow and no tests (3 of 10). 10 + 0 + 5 + 5 + 3 = 23.
Transparency & trusteditorial 39, provenance 61checked 6 November 2026 7%8.8 4.4
Closed service under terms naming Patoliya Infotech LLP in India, and the MCP server is MIT (18 of 30). The terms give retention periods (JSON results up to 6 months, HTML up to 1 month, search history indefinitely) and say personal data sits on DigitalOcean in India, and they advise EEA users not to use the service. The privacy policy is generic and neither document carries a date (15 of 30). No deprecation policy, and the terms allow products to be discontinued without notice (0 of 20). DigitalOcean in India named for account data; no sub-processor list (6 of 20). 18 + 15 + 0 + 6 = 39.
Negative events≤15None recorded0
Total42.4 · E

Weight is the published weight, and the figure under it is that category's share of the 100 points in this run. A pending category has no score and adds nothing. What changes when it's scored.

Score history no moves since it was graded

Every time a number on this listing moved, and what moved it: a change of terms or pricing, an outage, the vendor's own release, new evidence, or our own correction. A score can't change without an entry here. Every listing's changes · JSON · RSS

  1. Graded 42.4 E methodology v0.7

Fix list 21 items, the biggest gain first

Everything this grade says the listing lacks, from the reasons above, the checklist, the provenance checks, the deductions, what we couldn't check and what the review panel asked for, with the steps, ready to paste into a coding agent working on SERPHouse. A fix counts at the next check, once it's public.

What we couldn't check

  • Oxylabs. The home page says 'Explore the Scraper APIs Playground on the Oxylabs dashboard for hands-on interaction with our APIs', next to a SERPHouse signup button. The terms, privacy policy, about page and docs name no relationship with Oxylabs and no Oxylabs sub-processor, and the playground and signup are on serphouse.com. A search for the sentence found Oxylabs' own playground documentation but not the sentence, so where it came from is not established. Judgement call, not a deduction, since no claim of partnership is made; data/tools/oxylabs-web-scraper.json is a separate listing.
  • The pricing page lists '100% Success Rate' and a '99.99% Uptime SLA' on Basic and Regular; the docs list 99.95%, and say a 200 can carry an error to retry. No SLA terms or credits were found. Vendor claims, not deducted.
  • unchecked: GitHub issues and star counts, since the GitHub API refused us for its rate limit; repositories were read by shallow clone.
  • The docs name an official Python SDK, but no Python repository was found under github.com/SERPHouse and PyPI had no serphouse project we could read.
  • firstReleased is September 2019, when the about page says the first SERPHouse API launched; RDAP gives the domain 20 August 2019.
  • The lead said 4,000 free searches. The trial is 4,000 credits, and by the published prices a SERP request uses 10 credits, so about 400 SERP requests.
  • The trial terms forbid 'scraping at scale or performing automated bulk data extraction' with trial credits. Recorded as a fact.

Sources 13

  1. Home page serphouse.com · seen 2026-11-06
  2. About page and product timeline serphouse.com · seen 2026-11-06
  3. Getting started (auth, status codes, rate limits, pricing) serphouse.com · seen 2026-11-06
  4. MCP server docs serphouse.com · seen 2026-11-06
  5. Docs llms.txt serphouse.com · seen 2026-11-06
  6. Pricing serphouse.com · seen 2026-11-06
  7. Terms of service serphouse.com · seen 2026-11-06
  8. Privacy policy serphouse.com · seen 2026-11-06
  9. Contact page serphouse.com · seen 2026-11-06
  10. MCP server repository github.com · seen 2026-11-06
  11. npm package serphouse-mcp registry.npmjs.org · seen 2026-11-06
  12. Node.js SDK repository github.com · seen 2026-11-06
  13. Patoliya Infotech about page patoliyainfotech.com · seen 2026-11-06

Probe metrics

Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. The live panel above has what the pollers have seen so far, which doesn't change the score.

Pricing & changes

Paid $0.75 / 1k req Basic $29.99 a month for 400,000 credits ($0.75 per 1,000 SERP requests) and Regular $49.99 for 800,000 ($0.62). Autocomplete $0.37 and $0.31, Top 100 Google $7.50 and $6.25 per 1,000. Custom plans by email. Free trial 4,000 credits for 7 days, no card. Credits don't roll over.

Prices

ItemPriceUnitNote
SERP request, Basic$0.75per 1,000 requests$29.99 a month for 400,000 credits
SERP request, Regular$0.62per 1,000 requests$49.99 a month for 800,000 credits
Autocomplete request, Basic$0.37per 1,000 requests$0.31 on Regular
Top 100 Google SERP, Basic$7.50per 1,000 requests$6.25 on Regular
Basic plan$29.99per month (plan)400,000 credits, no rollover
Regular plan$49.99per month (plan)800,000 credits, no rollover

Compared across listings on the price index.

Recent changes

  • Latest release

Follow them as a feed at /feeds/tools/serphouse.xml, or this listing's score history at history.json.

Connect

Install

npx serphouse-mcp

First request

curl -X POST https://api.serphouse.com/serp/live \
  -H 'accept: application/json' \
  -H 'authorization: Bearer API_TOKEN' \
  -H 'content-type: application/json' \
  -d '{"data": {"domain": "google.com", "lang": "en", "q": "Coffee", "loc": "Texas,United States", "device": "desktop", "serp_type": "web"}}'

MCP client configuration

{
  "mcpServers": {
    "serphouse": {
      "url": "https://mcp.serphouse.com/YOUR_SERPHouse_API_KEY/mcp"
    }
  }
}

Through letme picks today, calling later

GET https://letme.dev/serphouse

letme.dev answers with this listing and how to call it direct, and picks the best tool for a job by capability or in words. Nothing on letme.dev is for people to look at; this page explains it.

Alternatives to SERPHouse

#23 of 25 in Best web search APIs for AI agents · All 308 search comparisons

SerpKite BTavily API + MCP BBSerpApi BKagi Search API CSearchAPI.io DSerper F

Head to head Web Search Tool on Amazon Bedrock AgentCore vs SERPHouse · Grounding with Bing Search vs SERPHouse · Brave Search API + MCP vs SERPHouse · Cloudflare Web Search API vs SERPHouse · DeepSeek Search and Fetch API vs SERPHouse · Exa API + MCP vs SERPHouse · Kagi Search API vs SERPHouse · Linkup vs SERPHouse · Mojeek Web Search API vs SERPHouse · Parallel Search and Task APIs vs SERPHouse · Perplexity Search API vs SERPHouse · SearchAPI.io vs SERPHouse · SerpApi vs SERPHouse · Serper vs SERPHouse · SERPHouse vs SpecStream · SERPHouse vs Tavily API + MCP · SERPHouse vs TinyFish Search · SERPHouse vs Valyu · SERPHouse vs You.com APIs · Fetch (MCP reference server) vs SERPHouse · NewsCatcher vs SERPHouse · SERPHouse vs SerpKite

Machine-readable

{} JSONM↓ MarkdownBadgeRSS

Similar toolGrade ScoreShared capabilitiesx402
SerpKite SerpKite (Anastasia Klimova, trading as SerpKite)B67.6web.search search.serp search.news search.images web.fetchno
Tavily API + MCP TavilyBB77.1web.search web.fetch search.news search.imagespartial
SerpApi SerpApiB63.5web.search search.serp search.news search.imagesno
Kagi Search API KagiC56.1web.search web.fetch search.news search.imagesno
SearchAPI.io SearchApiD50.1web.search search.serp search.news search.imagesno
Serper SerperF24.2web.search search.serp search.news search.imagesno

Machine-readable

For vendors

Verify this listing

For the vendor

Is this your product? Link to this page from your own site or README, then tell us where. It shows people and agents that the listing is yours and that you know it's here. It never changes a grade, rank or review.

  1. Add the badge or a link

    SERPHouse on Anchor Terminal, E, 42.4/100
    On a light page
    On a dark page
    <a href="https://www.anchorterminal.com/tools/serphouse"><img src="https://www.anchorterminal.com/badges/serphouse.svg" alt="SERPHouse on Anchor Terminal" height="20"></a>
    [![SERPHouse on Anchor Terminal](https://www.anchorterminal.com/badges/serphouse.svg)](https://www.anchorterminal.com/tools/serphouse)
    <a href="https://www.anchorterminal.com/tools/serphouse">SERPHouse on Anchor Terminal</a>

    It counts on a page on serphouse.com or one of its subdomains, or the README at the root of github.com/SERPHouse/serphouse-mcp.

  2. Tell us where it is

    We read it once now and again every week. If the link is missing two weeks in a row the listing says so, and a later check puts it back.

Agents send the same to POST /api/v1/verify as {"slug": "serphouse", "url": "…"}, or call the verify_listing tool at /mcp. Ten checks an hour from one address. What we check. To announce the listing, get sharing assets for social media.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report