Connect |
to 50+ data APIs
One API key for web scraping, search, social media data and enrichment — across every provider your agents need. Save money, better reliability, no subscriptions.
Works with
Use any capability—or pin the exact native endpoint
Use our automated routing or pick the exact native endpoint you need from the catalog.
Google Search
serper.search
Pin Serper when you want provider-native Google search behavior
Web Scraping
firecrawl.scrape
Scrape pages through the exact Firecrawl endpoint from `/api/v2/run`
Research
perplexity.search
Reach directly for Perplexity when the upstream search product matters
Keyword Ideas
dataforseo.dataforseo_labs_google_keyword_ideas
Use a deep provider endpoint without juggling separate auth and billing
YouTube Transcript
scrapecreators.youtube_transcript
Get full transcripts from any YouTube video for research and competitive analysis
Email Verification
hunter.domain_search
Find all verified emails for a domain without juggling a separate Hunter subscription
Social Profile Data
scrapecreators.twitter_profile
Pull Twitter/X profile data—follower counts, bio, pinned posts—for any public account
Headless Scraping
spidercloud.scrape
JavaScript-rendered scraping via SpiderCloud for pages that block lightweight scrapers
One interface, three surfaces
Start in the CLI, add MCP or HTTP when you need it
# Install & authenticate $ npm install -g dumplingai-cli $ dumplingai init # Run a capability (auto-routes to best provider) $ dumplingai run capability scrape_page \ --input '{"url": "https://example.com", "format": "markdown"}'
Why teams choose DumplingAI
One API key, not twelve
Stop managing separate subscriptions for search, scraping, transcripts, and extraction. One API key, one bill, one dashboard.
Smart routing
Let DumplingAI pick the best provider for each job, or drop down to native provider endpoints when you want more control.
See what your agents spend
Every call logged with cost and latency. Per-agent spend controls. No surprise bills.
Works with your stack
API, CLI, MCP Server. Claude Code, OpenClaw, Cursor, Codex, or your own runtime.
Pin exact endpoints without losing the control plane
Use provider-native ids when exact upstream behavior matters, while DumplingAI keeps auth, logging, and spend controls in one place
Your Agent
DumplingAI
Providers
Transparent usage across the unified catalog
Search once, pin the right endpoint, and inspect spend in one place.
Serper
serper.search
Track usage in Workbench and pricing
Firecrawl
firecrawl.scrape
Track usage in Workbench and pricing
Perplexity
perplexity.search
Track usage in Workbench and pricing
DataForSEO
dataforseo.dataforseo_labs_google_keyword_ideas
Track usage in Workbench and pricing
Ship your first agent workflow in 30 seconds
Install the CLI, add your API key, done. Free tier included.