Scrapingdog
NPM · SCRAPINGDOG-MCP · SCANNED SEP 20
Scrapingdog web-scraping & SERP APIs: web scrape, Google, Amazon, LinkedIn, YouTube, and more.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 50 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability71
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 5181 tokens (~148/item across 35 items; 35 tools + 0 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 Management93
- Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "chatgpt" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 35 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
How do I install the Scrapingdog MCP server?
Scrapingdog runs locally as an npm package, launched with npx -y scrapingdog-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · scrapingdog-mcp
claude mcp add darshan972-scrapingdog-mcp -- npx -y scrapingdog-mcp
{
"mcpServers": {
"darshan972-scrapingdog-mcp": {
"command": "npx",
"args": [
"-y",
"scrapingdog-mcp"
]
}
}
} {
"servers": {
"darshan972-scrapingdog-mcp": {
"command": "npx",
"args": [
"-y",
"scrapingdog-mcp"
]
}
}
} codex mcp add darshan972-scrapingdog-mcp -- npx -y scrapingdog-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"darshan972-scrapingdog-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"scrapingdog-mcp"
],
"enabled": true
}
}
} openclaw mcp add darshan972-scrapingdog-mcp --command npx --arg -y --arg scrapingdog-mcp
mcp_servers:
darshan972-scrapingdog-mcp:
command: "npx"
args: ["-y", "scrapingdog-mcp"] {
"McpServers": {
"darshan972-scrapingdog-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"scrapingdog-mcp"
]
}
}
} assistant mcp add darshan972-scrapingdog-mcp -t stdio -c npx -a -y scrapingdog-mcp
{
"mcpServers": {
"darshan972-scrapingdog-mcp": {
"command": "npx",
"args": [
"-y",
"scrapingdog-mcp"
]
}
}
} 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.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 −4
- Stability: pass → 0.77 functional
- 14 Sept 26 +1
- Stability: 0.97 → pass security
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Sept 26 0
- Security disclosure: unverified → fail ▼ functional
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 20 Sept 2026 · Analysed npm/scrapingdog-mcp@0.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
amazon_offers Amazon Offers API ~83
Fetch all buying offers and sellers for an Amazon product by ASIN.
| Name | Type | Req | Description |
|---|---|---|---|
| asin | string | yes | Amazon ASIN of the product. |
| country | string | – | Two-letter ISO marketplace country code. (API default: us) |
| domain | string | – | Amazon TLD, e.g. com, in, de, co.uk. (API default: com) |
No output schema declared.
No examples provided.
amazon_product Amazon Product API ~109
Scrape a single Amazon product page (price, specs, ratings) by ASIN.
| Name | Type | Req | Description |
|---|---|---|---|
| asin | string | yes | Amazon Standard Identification Number (ASIN) of the product. |
| country | string | – | Two-letter ISO marketplace country code. (API default: us) |
| domain | string | – | Amazon TLD, e.g. com, in, de, co.uk. (API default: com) |
| postal_code | string | – | Postal/ZIP code to localize price and availability. |
No output schema declared.
No examples provided.
amazon_reviews Amazon Reviews API ~107
Scrape customer reviews, ratings and reviewer details for an Amazon product by ASIN.
| Name | Type | Req | Description |
|---|---|---|---|
| asin | string | yes | Amazon ASIN of the product. |
| country | string | – | Two-letter ISO marketplace country code. (API default: us) |
| domain | string | – | Amazon TLD, e.g. com, in, de, co.uk. (API default: com) |
| page | number | – | Reviews page number, starting at 1. (API default: 1) |
No output schema declared.
No examples provided.
amazon_search Amazon Search API ~162
Scrape Amazon search-result listings for a query.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | yes | Two-letter ISO marketplace country code. (API default: us) |
| domain | string | yes | Amazon TLD, e.g. com, in, de, co.uk. (API default: com) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| page | number | yes | Page number, starting at 1. (API default: 1) |
| postal_code | string | – | Postal/ZIP code to localize results. |
| premium | boolean | – | Use premium proxies (raises success rate; extra credits). (API default: false) |
| query | string | yes | Amazon search query. |
No output schema declared.
No examples provided.
baidu_search Baidu Search API ~144
Scrape Baidu (Chinese-market) search results as structured JSON.
| Name | Type | Req | Description |
|---|---|---|---|
| ct | string | – | Language filter: 1=all, 2=Simplified Chinese, 3=Traditional Chinese. |
| html | boolean | – | Return raw HTML instead of parsed JSON. (API default: false) |
| pn | number | – | Pagination offset (0=first page, 10=second, ...). (API default: 0) |
| query | string | yes | Baidu search query; supports Baidu operators (site:, inurl:, intitle:). |
| rn | number | – | Results per page (max 50). (API default: 10) |
No output schema declared.
No examples provided.
bing_search Bing Search API ~145
Scrape Bing search results as structured JSON.
| Name | Type | Req | Description |
|---|---|---|---|
| cc | string | – | Two-letter ISO country code. Mutually exclusive with mkt. |
| count | number | – | Results per page (1-50). |
| first | number | – | Result offset to start from. (API default: 1) |
| lat | string | – | GPS latitude for the search origin. |
| lon | string | – | GPS longitude for the search origin. |
| mkt | string | – | Market as language-country, e.g. en-US. Mutually exclusive with cc. |
| query | string | yes | Bing search query; supports standard Bing operators. |
| safeSearch | string | – | Content filter level. |
No output schema declared.
No examples provided.
chatgpt ChatGPT Scraper API ~60
Send a prompt to ChatGPT and get the response as structured JSON, at scale.
| Name | Type | Req | Description |
|---|---|---|---|
| html | boolean | – | Return raw HTML instead of parsed JSON. (API default: false) |
| prompt | string | yes | The prompt to send to ChatGPT. |
No output schema declared.
No examples provided.
ebay_search eBay Search API ~72
Scrape eBay search listings from an eBay search URL.
| Name | Type | Req | Description |
|---|---|---|---|
| html | boolean | – | Return raw HTML instead of parsed JSON. (API default: false) |
| url | string | yes | Full eBay search URL, e.g. https://www.ebay.com/sch/i.html?_nkw=laptop. |
No output schema declared.
No examples provided.
google_ai_mode Google AI Mode API ~146
Retrieve Google's AI Mode conversational answer for a query.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| html | boolean | – | Return raw HTML instead of parsed JSON. (API default: false) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| location | string | – | Search origin location. Incompatible with uule. |
| query | string | yes | The query to search in Google AI Mode. |
| safe | string | – | Adult-content filter. (API default: off) |
No output schema declared.
No examples provided.
google_ai_overview Google AI Overview API ~68
Fetch the Google AI Overview block for a search. Pass the AI-overview URL returned in a google_search response (that URL expires ~2 minutes after it is issued).
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | AI Overview URL taken from a google_search response. Expires ~2 minutes after issuance. |
No output schema declared.
No examples provided.
google_finance Google Finance API ~99
Fetch live stock quotes and market data from Google Finance.
| Name | Type | Req | Description |
|---|---|---|---|
| html | boolean | – | Return raw HTML instead of parsed JSON. (API default: false) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| query | string | yes | Ticker in Google Finance format, e.g. GOOGL:NASDAQ or NIFTY_50:INDEXNSE. |
No output schema declared.
No examples provided.
google_hotels Google Hotels API ~395
Get hotel and vacation-rental prices, ratings and availability from Google Hotels.
| Name | Type | Req | Description |
|---|---|---|---|
| adults | number | – | Number of adults. (API default: 2) |
| check_in_date | string | yes | Check-in date, YYYY-MM-DD. |
| check_out_date | string | yes | Check-out date, YYYY-MM-DD. |
| children | number | – | Number of children. (API default: 0) |
| children_ages | string | – | Comma-separated child ages 1-17 (e.g. '5,8,10'). |
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| currency | string | – | Pricing currency. (API default: USD) |
| free_cancellation | boolean | – | Only show free-cancellation options. |
| hotel_class | string | – | Star class filter (2-5), comma-separated. |
| html | boolean | – | Return raw HTML instead of parsed JSON. (API default: false) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| max_price | number | – | Maximum price filter. |
| min_price | number | – | Minimum price filter. |
| next_page_token | string | – | Pagination token from a previous response. |
| property_token | string | – | Token for detailed property information. |
| query | string | yes | Hotel search query (e.g. 'hotels in Paris'). |
| rating | string | – | Min rating: 7=3.5+, 8=4.0+, 9=4.5+. |
| sort_by | string | – | Sort: 3=lowest price, 8=highest rating, 13=most reviews. |
| vacation_rentals | boolean | – | Search vacation rentals instead of hotels. (API default: false) |
No output schema declared.
No examples provided.
google_images Google Images API ~192
Get Google Images search results with sources and thumbnails.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| domain | string | – | Country-specific Google domain (e.g. google.co.uk, google.co.in). (API default: google.com) |
| html | boolean | – | Return raw HTML instead of parsed JSON. (API default: false) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| query | string | yes | Image search query. |
| safe | string | – | Adult-content filter. (API default: off) |
| start | number | – | Result offset (e.g. 20 skips the first 20). |
| tbs | string | – | Advanced filter (size, color, type, time range). |
No output schema declared.
No examples provided.
google_immersive_product Google Immersive Product API ~138
Retrieve detailed product info from Google's immersive product popup via a page token.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| page_token | string | yes | Immersive-product token (from a Google Shopping/Search response). |
| sori | string | – | Seller pagination cursor; works with stores. |
| stores | boolean | – | Enable seller pagination (requires sori). (API default: false) |
No output schema declared.
No examples provided.
google_jobs Google Jobs API ~157
Scrape job listings aggregated across Google Jobs.
| Name | Type | Req | Description |
|---|---|---|---|
| chips | string | – | Extra query filters from the Google Jobs UI. |
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| domain | string | – | Country-specific Google domain (e.g. google.co.uk, google.co.in). (API default: google.com) |
| language | string | – | Result language, e.g. en_us. (API default: en_us) |
| ltype | string | – | Work-from-home filter. |
| next_page_token | string | – | Token from a previous response to fetch the next page. |
| query | string | yes | Job search query. |
No output schema declared.
No examples provided.
google_lens Google Lens API ~164
Reverse-image search via Google Lens for visual matches and products.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| exact_matches | boolean | – | Enable exact-match results. (API default: false) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| product | boolean | – | Enable product results. (API default: false) |
| query | string | – | Optional text query to run alongside the image. |
| url | string | yes | URL of the image to run through Google Lens. |
| visual_matches | boolean | – | Enable visual-match results. (API default: false) |
No output schema declared.
No examples provided.
google_maps Google Maps API ~231
Scrape local business listings and place details from Google Maps.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| data | string | – | Google Maps 'data' filter string copied from a Maps URL. |
| domain | string | – | Country-specific Google domain (e.g. google.co.uk, google.co.in). (API default: google.com) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| ll | string | – | GPS origin as @latitude,longitude,zoom (e.g. @40.7,-74.0,14z). Required for pagination. |
| page | number | – | Pagination offset; increment by 20. Requires ll. (API default: 0) |
| place_id | string | – | Unique Google Maps place identifier (for place lookups). |
| query | string | yes | Google Maps search query, e.g. 'pizza'. |
| type | string | – | Result type. |
No output schema declared.
No examples provided.
google_news Google News API ~192
Scrape Google News headlines, sources and timestamps.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| publication_token | string | – | Publisher identifier. Mutually exclusive with query. |
| query | string | – | Search terms. Supports operators like site: and when:. Cannot combine with *_token params. |
| section_token | string | – | Subsection token; only with topic_token or publication_token. |
| so | string | – | Sort order (only with story_token): 0 = relevance, 1 = date. (API default: 0) |
| topic_token | string | – | Topic identifier (World, Business, Technology, ...). Mutually exclusive with query. |
No output schema declared.
No examples provided.
google_patents Google Patents API ~233
Search patent records and metadata via Google Patents.
| Name | Type | Req | Description |
|---|---|---|---|
| after | string | – | Min date as type:YYYYMMDD (type = priority|filing|publication). |
| assignee | string | – | Comma-separated assignee names. |
| before | string | – | Max date as type:YYYYMMDD (type = priority|filing|publication). |
| country | string | – | Comma-separated country codes (e.g. WO,US). |
| inventor | string | – | Comma-separated inventor names. |
| language | string | – | Comma-separated languages (e.g. ENGLISH,GERMAN). |
| num | number | – | Results per page (1-100). (API default: 10) |
| page | number | – | Zero-based page number. (API default: 0) |
| query | string | yes | Search terms; separate multiple with semicolons. |
| scholar | boolean | – | Include Google Scholar results. (API default: false) |
| sort | string | – | Sort order. |
| status | string | – | Filter by status. |
| type | string | – | Filter by type. |
No output schema declared.
No examples provided.
google_scholar Google Scholar API ~160
Search academic papers, authors and citation counts via Google Scholar.
| Name | Type | Req | Description |
|---|---|---|---|
| as_sdt | string | – | Search type / filter (patents, case law, courts). |
| as_yhi | string | – | Filter: results up to this year. |
| as_ylo | string | – | Filter: results from this year onward. |
| cites | string | – | Article id for 'Cited by' searches. |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| page | number | – | Zero-based page number. (API default: 0) |
| query | string | – | Search query (optional when using cites). |
| results | number | – | Results per page. |
No output schema declared.
No examples provided.
google_search Google Search (SERP) API ~300
Scrape real-time Google Search results as structured JSON (organic results, ads, knowledge graph, people-also-ask, etc.).
| Name | Type | Req | Description |
|---|---|---|---|
| advance_search | boolean | – | Enable rich feature snippets (extra credits). (API default: false) |
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| domain | string | – | Country-specific Google domain (e.g. google.co.uk, google.co.in). (API default: google.com) |
| html | boolean | – | Return the full HTML of the Google page instead of parsed JSON. (API default: false) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| location | string | – | Search origin location, ideally at city level. Incompatible with uule. |
| mob_search | boolean | – | Return mobile search results. (API default: false) |
| page | number | – | Zero-based page number (0 = first page). (API default: 0) |
| query | string | yes | Search query. Supports operators like site:, inurl:, intitle:. |
| results | number | – | Number of results to return per page. |
| safe | string | – | Adult-content filter. (API default: off) |
| tbs | string | – | Advanced filter for time ranges / verbatim mode. |
No output schema declared.
No examples provided.
google_shopping Google Shopping API ~183
Scrape product listings and prices from Google Shopping.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| domain | string | – | Country-specific Google domain (e.g. google.co.uk, google.co.in). (API default: google.com) |
| html | boolean | – | Return raw HTML instead of parsed JSON. (API default: false) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| page | number | – | Zero-based page number. (API default: 0) |
| query | string | yes | Product search term. |
| safe | string | – | Adult-content filter. (API default: off) |
| tbs | string | – | Advanced result filter. |
No output schema declared.
No examples provided.
google_shorts Google Shorts API ~226
Retrieve Google short videos with sources, thumbnails and dates.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| domain | string | – | Country-specific Google domain (e.g. google.co.uk, google.co.in). (API default: google.com) |
| html | boolean | – | Return raw HTML instead of parsed JSON. (API default: false) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| lr | string | – | Restrict results to specific language(s). |
| nfpr | string | – | Set 1 to exclude auto-corrected misspellings. (API default: 0) |
| query | string | yes | Search query. |
| safe | string | – | Adult-content filter. (API default: off) |
| start | number | – | Result offset (e.g. 12 skips the first 12). |
| tbs | string | – | Advanced result filter. |
No output schema declared.
No examples provided.
google_trends Google Trends API ~218
Track keyword search interest over time and by region via Google Trends.
| Name | Type | Req | Description |
|---|---|---|---|
| cat | string | – | Category id. (API default: 0) |
| data_type | string | – | Type of Trends data. (API default: TIMESERIES) |
| date | string | – | Time range: e.g. 'now 1-H', 'now 7-d', 'today 12-m', 'all', or 'yyyy-mm-dd yyyy-mm-dd'. |
| geo | string | – | Location origin (e.g. US, GB). Defaults to worldwide. |
| gprop | string | – | Property filter. |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| query | string | yes | Up to 5 comma-separated terms (1 for map-only types); max 100 chars each. |
| region | string | – | Map granularity. |
| tz | string | – | Timezone offset in minutes (-1439..1439). (API default: 420) |
No output schema declared.
No examples provided.
linkedin_profile LinkedIn Profile / Company API ~95
Scrape a public LinkedIn person or company profile by its public identifier (the slug in the profile URL).
| Name | Type | Req | Description |
|---|---|---|---|
| linkId | string | yes | The public LinkedIn id/slug, e.g. 'williamhgates' for linkedin.com/in/williamhgates. |
| premium | boolean | – | Use premium mode for higher success rate. (API default: false) |
| type | string | yes | Profile type to scrape. |
No output schema declared.
No examples provided.
screenshot Screenshot API ~147
Capture a screenshot (PNG/JPG/WEBP) of any web page. Returns the image.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Image format. (API default: png) |
| fullPage | boolean | – | Capture the full scrollable page instead of just the viewport. (API default: false) |
| height | number | – | Viewport height in pixels. |
| quality | number | – | Image quality 0-100 (jpg/webp). (API default: 80) |
| url | string | yes | URL of the page to screenshot. |
| wait_until | string | – | Navigation completion trigger. (API default: domcontentloaded) |
| width | number | – | Viewport width in pixels. |
No output schema declared.
No examples provided.
universal_search Universal Search API ~91
Single endpoint that scrapes major search engines and returns unified organic results.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| query | string | yes | Search query. |
No output schema declared.
No examples provided.
walmart_search Walmart Search API ~44
Scrape Walmart search results from a Walmart search URL.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Full Walmart search URL, e.g. https://www.walmart.com/search?q=football. |
No output schema declared.
No examples provided.
web_scrape Web Scraping API ~258
General-purpose web scraper. Fetches any URL through Scrapingdog's rotating proxies with optional JavaScript rendering, premium proxies, geo-targeting, and AI-based extraction. Returns the page HTML (or extracted data).
| Name | Type | Req | Description |
|---|---|---|---|
| ai_extract_rules | string | – | JSON string of field->instruction rules for structured AI extraction. |
| ai_query | string | – | Natural-language instruction to extract specific data from the page via AI. |
| country | string | – | Two-letter ISO country code for the proxy geo-location (requires premium). (API default: us) |
| dynamic | boolean | – | Set true to render JavaScript with a headless browser. Costs more credits. (API default: false) |
| markdown | boolean | – | Return the page content converted to clean markdown instead of raw HTML. (API default: false) |
| premium | boolean | – | Set true to use premium (residential) proxies for hard-to-scrape sites. (API default: false) |
| session_number | number | – | Reuse the same proxy IP across requests by passing a stable integer. |
| url | string | yes | The absolute URL of the page to scrape. |
| wait | number | – | Milliseconds to wait after page load before capturing (only with dynamic=true). |
No output schema declared.
No examples provided.
x_profile X (Twitter) Profile API ~54
Scrape a public X (Twitter) profile's metadata (bio, followers, counts, etc.).
| Name | Type | Req | Description |
|---|---|---|---|
| profileId | string | yes | X username or user id, e.g. 'elonmusk' or 'nasa'. |
No output schema declared.
No examples provided.
youtube_channel YouTube Channel API ~90
Get a YouTube channel's details and videos.
| Name | Type | Req | Description |
|---|---|---|---|
| channel_id | string | yes | YouTube channel id. |
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
No output schema declared.
No examples provided.
youtube_comments YouTube Comments API ~97
Get comments for a YouTube video.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| v | string | yes | YouTube video id (the part after ?v= in the URL). |
No output schema declared.
No examples provided.
youtube_search YouTube Search API ~118
Retrieve YouTube search results with video titles and metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| search_query | string | yes | YouTube search query, e.g. 'elon musk interview'. |
| sp | string | – | Pagination/filter token; pass next_page_token from a previous response. |
No output schema declared.
No examples provided.
youtube_transcripts YouTube Transcripts API ~103
Get the transcript (with timestamps) for a YouTube video.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| v | string | yes | YouTube video id (the part after ?v= in the URL). |
No output schema declared.
No examples provided.
youtube_video YouTube Video API ~100
Get details and metadata for a single YouTube video.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Two-letter ISO country code to geo-target results (e.g. us, gb, in, de). (API default: us) |
| language | string | – | Result language code (e.g. en, es, fr, de). (API default: en) |
| v | string | yes | YouTube video id (the part after ?v= in the URL). |
No output schema declared.
No examples provided.
What is the Scrapingdog MCP server?
Scrapingdog is an MCP server listed in the public MCP registry as io.github.Darshan972/scrapingdog-mcp. Scrapingdog web-scraping & SERP APIs: web scrape, Google, Amazon, LinkedIn, YouTube, and more. This page covers its npm package (scrapingdog-mcp).
Is the Scrapingdog MCP server safe to use?
Scrapingdog scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 Scrapingdog MCP server expose?
Scrapingdog exposes 35 tools: web_scrape, google_search, google_maps, google_news, google_trends, and 30 more. Their descriptions and schemas cost roughly 5,181 tokens of context every time the server is loaded.
Is the Scrapingdog MCP server still maintained?
Scrapingdog is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Scrapingdog MCP server under?
Scrapingdog declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.