Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Scrappa

REMOTE · SCRAPPA.CO

Scraping API for Google Search, Maps, Flights, Jobs, YouTube, LinkedIn, Trustpilot and more.

Available components

0 this week 86 Trust /100

Last scanned (20 hours ago)

Scores higher than 88% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Web Scraping

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security74
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability78
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2386 tokens (~170/item across 14 items; 13 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 18 Nov 26 0
    • A breaking change shipped without a version bump: still 2.0.0 ▼ security
    • Tool “goodrx_drug” was removed ▼ security
    • Tool “goodrx_drug_info” was removed ▼ security
    • Tool “goodrx_search” was removed ▼ security
    • New tool “pricerunner_data” functional
    • New tool “pricespy_data” functional
  • 17 Nov 26 0
    • Schema quality: 2064 → 2394 ▼ functional
    • New tool “goodrx_drug” functional
    • New tool “goodrx_drug_info” functional
    • New tool “goodrx_search” functional
  • 11 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 9 Nov 26 +1
    • Stability: 0.97 → pass security
  • 8 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 1 Nov 26 +6
    • Stability: fail → pass ▲ security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://scrappa.co/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=scrappa.co CN=WE1,O=Google Trust Services,C=US 15 Nov 2026 13 Feb 2027 ECDSA 256 ECDSA-SHA256 6d62728df1ec76bb1361b6281e758552
SANs: scrappa.co, *.scrappa.co
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of scrappa.co. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
co. DS published 7786 8 Verified
scrappa.co. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
x-content-type-options nosniff
x-frame-options SAMEORIGIN

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://scrappa.co/mcp Verified 200
http (plaintext) http://scrappa.co/mcp HTTPS enforced 301 https://scrappa.co/mcp
MCP tools · 13 exposed · ~2,171 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
call-endpoint ~106

Fetch data from a Scrappa API endpoint, including data from third-party sites. Use Find API endpoints to discover an endpoint and its parameters. Requests may use credits on your Scrappa account.

NameTypeReqDescription
endpointstringyesThe endpoint name from search-endpoints results (e.g. "kununu-search", "simple-search")
paramsstring–JSON object of parameters to pass to the endpoint (e.g. {"query": "pizza berlin", "page": "1"})

No output schema declared.

No examples provided.

geizhals_get_price_history ~152

Get the best-price history of one Geizhals product by its product_id. Returns the current best price, the all-time lowest and highest best price, and the dates on which the best price changed within the chosen window (each entry is valid until the next one). Reads public data only.

NameTypeReqDescription
daysinteger–History window in days, 1 to 3650. Default: 90.
marketstring–Geizhals market: de (Germany), at (Austria) or eu (EU). Default: de.
product_idstringyesGeizhals product id, e.g. "2795961", or a Geizhals product link.

No output schema declared.

No examples provided.

geizhals_get_product ~196

Get one Geizhals product by its product_id (from geizhals_search_products or a Geizhals link like "...-a2795961.html"). Returns the best and average price, the number of offers, current shop offers (shop, price, availability, shipping), full specifications, test review scores and the Geizhals link. Shop owner names and contact data are never returned. Reads public data only.

NameTypeReqDescription
languagestring–Language of names and specifications. Default: de.
marketstring–Geizhals market: de (Germany), at (Austria) or eu (EU). Default: de.
offersinteger–Number of shop offers to return, cheapest first, 1 to 20. Default: 10.
product_idstringyesGeizhals product id, e.g. "2795961", or a Geizhals product link.

No output schema declared.

No examples provided.

geizhals_search_products ~216

Search the Geizhals price comparison (Germany, Austria, EU) by keyword, e.g. "samsung 990 pro 2tb". Returns per product: product_id, name, manufacturer, all-time lowest and highest best price, user rating, test score, key specifications and the Geizhals link. Use geizhals_get_product with a product_id for current shop prices and geizhals_get_price_history for the price trend. Reads public data only.

NameTypeReqDescription
languagestring–Language of names and specifications. Default: de.
limitinteger–Number of products to return, 1 to 20. Default: 10.
marketstring–Geizhals market: de (Germany), at (Austria) or eu (EU). Default: de.
pageinteger–Result page, starting at 1. Default: 1.
querystringyesProduct search words, e.g. "samsung 990 pro 2tb".

No output schema declared.

No examples provided.

google_flights_search ~214

Search public one-way flight offers on Google Flights between two airports on one date. For a round trip, search each direction separately. Returns per flight: price, airlines, flight numbers, departure and arrival times, duration and stops. It does not book or buy anything. Reads public data only.

NameTypeReqDescription
adultsinteger–Number of adult passengers, 1 to 9. Default: 1.
cabin_classstring–Cabin class. Default: economy.
currencystring–Currency code for prices, e.g. "EUR" or "USD". Default: USD.
departure_datestringyesDeparture date as YYYY-MM-DD.
destinationstringyesArrival airport IATA code, e.g. "LIS".
max_stopsstring–Maximum number of stops. Default: any.
originstringyesDeparture airport IATA code, e.g. "BER".
sort_bystring–Sort order. Default: top_flights.

No output schema declared.

No examples provided.

google_maps_get_reviews ~205

Read public Google Maps reviews of one place. Needs the business_id from google_maps_search_places. Returns per review: star rating, date, review text, review language and the owner reply. By default only reviews with text are returned. Reviewer names and profiles are never returned. Reads public data only.

NameTypeReqDescription
business_idstringyesThe business_id of the place, from google_maps_search_places, e.g. "0x47a851c655f20989:0x26bbfb4e84674c63".
include_rating_onlyboolean–Also return reviews that only have a star rating and no text. Default: false.
languagestring–Two-letter language code, e.g. "en" or "de". Default: en.
limitinteger–Number of reviews to return, 1 to 20. Default: 10.
sortstring–Order of the reviews. Default: newest.

No output schema declared.

No examples provided.

google_maps_search_places ~176

Search Google Maps for businesses and places, for example "pizza in Berlin Mitte" or "dentist near Alexanderplatz". Returns public business data: name, rating, number of reviews, category, address, website, phone, coordinates and a business_id. Use the business_id with google_maps_get_reviews to read reviews. Reads public data only.

NameTypeReqDescription
countrystring–Two-letter country code to focus the search, e.g. "de" or "us".
languagestring–Two-letter language code for the results, e.g. "en" or "de". Default: en.
limitinteger–Number of places to return, 1 to 20. Default: 10.
querystringyesWhat and where to search, e.g. "pizza in Berlin Mitte".

No output schema declared.

No examples provided.

google_search ~141

Search Google and get the organic web results for a query. Returns per result: position, title, link and snippet. Use it for current information from the web. Reads public data only.

NameTypeReqDescription
countrystring–Two-letter country code for local results, e.g. "us" or "de". Default: us.
languagestring–Two-letter language code, e.g. "en" or "de". Default: en.
numinteger–Number of results, 1 to 10. Default: 10.
querystringyesThe search query, e.g. "best coffee grinder 2026".

No output schema declared.

No examples provided.

pricerunner_data ~204

Read public PriceRunner data by action: suggest, search, category, category_filters, offers, price_history, reviews, product_info, navigation, sitemap, similar or detail. Detail needs the category id from search or the product url. Prices are numbers with currency and ids feed the next action. Public data only.

NameTypeReqDescription
actionstringyesThe PriceRunner data action to run.
catstring–Category id for category and similar.
categorystring–Category id from search (category_id). Required for detail unless url is given.
idstring–Product id from suggest or search.
idsstring–Comma-separated product ids for product_info.
offsetinteger–Result offset for search.
qstring–Search keyword for suggest and search.
sizeinteger–Page or result size.
urlstring–Product url from suggest or search. Supplies the category for detail.

No output schema declared.

No examples provided.

pricespy_data ~118

Read public PriceSpy data by action: autocomplete, search, categories, product or price_history. Product ids come from autocomplete or search. Prices are numbers with currency and cents are converted. Search returns the first result page only and has no page parameter. Public data only.

NameTypeReqDescription
actionstringyesThe PriceSpy data action to run.
categorystring–Category id from categories to scope a search.
idstring–Product id from autocomplete or search.
qstring–Search keyword for autocomplete and search.

No output schema declared.

No examples provided.

search-endpoints ~110

Find Scrappa API endpoints by keyword. Returns matching endpoint names, descriptions, and parameters. Use a returned endpoint name with Call an API endpoint.

NameTypeReqDescription
limitinteger–Maximum number of endpoints to return (default 25, max 50)
offsetinteger–Number of matching endpoints to skip, to read the next page (default 0)
querystringyesSearch term to find endpoints (e.g. "google maps reviews", "flights", "linkedin profile")

No output schema declared.

No examples provided.

trustpilot_get_company_reviews ~181

Read the public Trustpilot rating and reviews of a company by its website domain, e.g. "zalando.de". Returns the TrustScore, star rating, total review count and per review: rating, title, text, date and the company reply. Reviewer names and profiles are never returned. Reads public data only.

NameTypeReqDescription
domainstringyesCompany website domain, e.g. "zalando.de".
languagestring–Two-letter review language, e.g. "en" or "de". Default: all languages.
limitinteger–Number of reviews to return, 1 to 20. Default: 10.
sortstring–Order of the reviews. Default: recent.
starsstring–Only reviews with these star ratings, comma separated, e.g. "1,2".

No output schema declared.

No examples provided.

youtube_get_transcript ~152

Get the public transcript (captions) of a YouTube video. Accepts a video URL or video id. Returns English when available, otherwise the video language, unless you ask for a language. Returns the language and the full transcript text, cut at 40,000 characters for very long videos. Reads public data only.

NameTypeReqDescription
languagestring–Preferred transcript language code, e.g. "en" or "de". Default: English, or the video language when there is no English transcript.
videostringyesYouTube video URL or 11-character video id, e.g. "https://www.youtube.com/watch?v=dQw4w9WgXcQ".

No output schema declared.

No examples provided.

Install

How do I install the Scrappa MCP server?

Scrappa is a hosted endpoint at https://scrappa.co/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · scrappa.co

# add to Claude Code
claude mcp add --transport http co-scrappa-scrappa 'https://scrappa.co/mcp'
Common questions

What is the Scrappa MCP server?

Scrappa is an MCP server listed in the public MCP registry as co.scrappa/scrappa. Scraping API for Google Search, Maps, Flights, Jobs, YouTube, LinkedIn, Trustpilot and more. This page covers its hosted endpoint (https://scrappa.co/mcp).

Is the Scrappa MCP server safe to use?

Scrappa scores 86 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Scrappa MCP server expose?

Scrappa exposes 13 tools: search-endpoints, call-endpoint, google_maps_search_places, google_maps_get_reviews, google_flights_search, and 8 more. Their descriptions and schemas cost roughly 2,171 tokens of context every time the server is loaded.

Does the Scrappa MCP server require authentication?

No. We connected to Scrappa without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Scrappa MCP server still maintained?

Scrappa is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Scrappa MCP server?

VerifyMCP ran 13 checks on Scrappa, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.