ScrapingAnt MCP server
5 operations0 webhooks
Web scraping with ScrapingAnt - fetch a page as rendered HTML, as Markdown or as structured AI-extracted JSON, read the extended page data (cookies, headers, XHRs, iframes), and check credit usage.
Try ScrapingAnt with your agent
Connect ScrapingAnt, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.
Using Corsair, show me what you can do in ScrapingAnt on my account, then run one read-only example and show me the result.
ScrapingAnt tools and triggers
Tools are what your agent can do in ScrapingAnt through Corsair's MCP server. Triggers are the ScrapingAnt events a routine can start from.
Scrape
- ExtendedRead-only
Fetch a page and return HTML, text, cookies, headers, status code, XHRs and iframes as JSON; spends 1 to 125 credits
scrape.extended
- HtmlRead-only
Fetch a page and return its HTML, with the target page status and credit cost; spends 1 to 125 credits depending on browser and proxy
scrape.html
- MarkdownRead-only
Fetch a page and return the whole thing as Markdown, ready for an LLM; spends 1 to 125 credits
scrape.markdown
Account
- UsageRead-only
Read the active plan, its period and the credits left in it; costs nothing
account.usage
Extract
- DataRead-only
Fetch a page and have an AI model extract the requested properties as a JSON object; spends the scrape cost plus 1 credit per 30 characters of page and output text
extract.data
Connect ScrapingAnt to Claude, ChatGPT or Cursor
- 1
Connect ScrapingAnt in Corsair
Add your ScrapingAnt API key once in Corsair. Corsair stores the credential encrypted and makes the ScrapingAnt API calls for your agent, so it never goes into a prompt or a config file. Connect ScrapingAnt
If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs ScrapingAnt. On a ChatGPT personal plan, connect ScrapingAnt here first.
- 2
Add Corsair's MCP server to your agent
Every client uses the same address:
https://mcp.corsair.dev/mcpOpen Customize → Connectors → Add custom connector, paste the address, then select Connect.Add a custom MCP server with the address and choose OAuth. Personal plans get read tools only.Add to CursorOr add this to~/.cursor/mcp.json. Cursor opens Corsair to sign in the first time it connects.{ "mcpServers": { "corsair": { "url": "https://mcp.corsair.dev/mcp" } } }Run this, then run/mcpin Claude Code to sign in.claude mcp add --transport http corsair https://mcp.corsair.dev/mcpCodex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client
- 3
Sign in and choose what needs your approval
Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. Every ScrapingAnt operation only reads data, so it runs right away in every mode.
FAQ
Install corsair and @corsair-dev/scrapingant, add the ScrapingAnt plugin, and connect with an API key. Then call methods like corsair.scrapingant.api.account.usage() from your app. Corsair keeps each tenant isolated.
Yes. ScrapingAnt requires an API key from your ScrapingAnt account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.
Yes. One Corsair client can hit ScrapingAnt, GitHub, Notion, Stripe, and the rest. Trigger ScrapingAnt from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.
Teams use Corsair for web scraping with ScrapingAnt - fetch a page as rendered HTML, as Markdown or as structured AI-extracted JSON, read the extended page data (cookies, headers, XHRs, iframes), and check credit usage. Common builds include sync jobs, admin tooling, and agents that call ScrapingAnt APIs from your backend.
The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per ScrapingAnt API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.
We maintain @corsair-dev/scrapingant in the open repo. When ScrapingAnt ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.
No. Corsair does not read your ScrapingAnt data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store ScrapingAnt data on your behalf.
Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.
Yes. Put ScrapingAnt on a link in Strict mode and every write waits for your approval, while destructive actions are refused. Every ScrapingAnt operation only reads data, so there are no changes to approve today. You can change a link's mode at hub.corsair.dev/me.