scrapingdog-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCRAPINGDOG_API_KEY | Yes | Your Scrapingdog API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scrapeA | Scrape any URL via the Scrapingdog Web Scraping API (/scrape). Returns the page's HTML. Supports JS rendering (dynamic), premium residential proxies, geotargeting (country), sessions, stealth/captcha bypass, and a render wait. Costs 1–25 credits depending on options. |
| screenshotB | Capture a screenshot of a URL via the Scrapingdog Screenshot API (/screenshot). Supports full-page capture, viewport size, wait-until, format (png/jpg/webp), and quality. Costs 5 credits. Note: this tool reports image metadata; binary bytes aren't returned as text. |
| google_searchA | Run a Google search via Scrapingdog (/google). Returns organic results, ads, knowledge graph, and other SERP features as JSON (or raw HTML with html=true). Supports localization, pagination, advanced filters, and mobile results. Costs 5–10 credits. |
| bing_searchA | Run a Bing search via Scrapingdog (/bing/search). Returns parsed Bing results as JSON. Supports market/country targeting, geo coordinates, pagination, and safe-search filters. |
| duckduckgo_searchA | Run a DuckDuckGo search via Scrapingdog (/duckduckgo/search). Returns parsed results as JSON. Supports region (kl), date filters (df), and pagination via next_page_token (15 per page). |
| baidu_searchA | Run a Baidu search via Scrapingdog (/baidu/search). Returns parsed results as JSON. Supports Chinese-language restriction (ct), pagination (pn), and result count (rn). |
| x_profileA | Scrape an X (Twitter) profile via Scrapingdog (/x/profile). Returns the profile's name, handle, follower counts, bio, and other public metadata as JSON. Pass a username or user ID. |
| x_postA | Scrape an X (Twitter) post (tweet) via Scrapingdog (/x/post). Pass the numeric tweet ID from the post URL. |
| datacenter_proxyA | Return Scrapingdog Datacenter Proxy connection details (host, port, username, password) and a ready-to-paste curl/Python example. This is a forward proxy (proxy.scrapingdog.com:8081), not an HTTP API — point your own HTTP client at it. Optionally pass target_url for a ready-to-run curl. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool targets a distinct resource or action: raw HTML scraping, screenshots, four search engines, X profile/post, and proxy details. The search tools are differentiated by the named engine, and the X tools by profile vs post, leaving no ambiguous overlaps.
Tool names use a mix of verb forms and noun compounds, such as scrape, screenshot, google_search, x_profile, and datacenter_proxy. While the snake_case style is consistent, there is no uniform verb_noun pattern, making the naming somewhat mixed.
With 9 tools covering scraping, screenshots, search, social media, and proxy access, the count is well within the ideal 3-15 range and each tool earns its place.
The set covers core Scrapingdog features (scrape, screenshot, search engines, X data, proxy) with only minor gaps such as missing X search or timeline and other less-used Scrapingdog endpoints. Agents can work around these gaps by using the scrape tool.