← All integrations

Scrape.do MCP server

11 operations0 webhooks

Web scraping with Scrape.do - fetch pages as HTML, Markdown, JSON network reports or screenshots through rotating proxies, and run bulk URL jobs asynchronously.

Use Scrape.do in Claude, ChatGPT, Cursor or another MCP client

Connect Scrape.do once in Corsair, then add one MCP address to your agent.

Connect Scrape.do
Setup steps for Claude, ChatGPT, Cursor and Claude Code

Building your own app on the Corsair SDK? Get API keys

Try Scrape.do with your agent

Connect Scrape.do, 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 Scrape.do on my account, then run one read-only example and show me the result.

Runs once, when you ask

Scrape.do tools and triggers

Tools are what your agent can do in Scrape.do through Corsair's MCP server. Triggers are the Scrape.do events a routine can start from.

Scrape

  • HtmlRead-only

    Fetch a page through the proxy with its status code; costs credits that vary by proxy and rendering

    scrape.html

  • JsonRead-only

    Fetch a page as a JSON report with its status, content and network requests

    scrape.json

  • MarkdownRead-only

    Fetch a page and return it converted to Markdown

    scrape.markdown

  • ScreenshotRead-only

    Render a page in the headless browser and return base64 PNG screenshots

    scrape.screenshot

Account

  • Async InfoRead-only

    Read the async pool concurrency, active jobs and credits left; costs nothing

    account.asyncInfo

  • InfoRead-only

    Read the subscription state, concurrency limit and requests left this month; costs nothing but is limited to 10 calls a minute

    account.info

Jobs

  • CancelWrite

    Cancel a queued or running job; a finished job cannot be cancelled

    jobs.cancel

  • GetRead-only

    Read an async job with its status and one entry per target

    jobs.get

  • ListRead-only

    List async jobs with paging

    jobs.list

  • ResultRead-only

    Read one task result with the page content, its status and when it expires

    jobs.result

  • StartWrite

    Start an async job for up to 100 URLs and return its job and task ids; results are held by Scrape.do until they expire

    jobs.start

Connect Scrape.do to Claude, ChatGPT or Cursor

  1. 1

    Connect Scrape.do in Corsair

    Add your Scrape.do API key once in Corsair. Corsair stores the credential encrypted and makes the Scrape.do API calls for your agent, so it never goes into a prompt or a config file. Connect Scrape.do

    If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Scrape.do. On a ChatGPT personal plan, connect Scrape.do here first.

  2. 2

    Add Corsair's MCP server to your agent

    Every client uses the same address:

    https://mcp.corsair.dev/mcp
    Open Customize → Connectors → Add custom connector, paste the address, then select Connect.

    Codex, 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. 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. None of Scrape.do's operations are destructive, so in the default Cautious mode they all run right away. Strict mode asks before each of its 2 writes, and Read mode allows reads only.

FAQ

Install corsair and @corsair-dev/scrapedo, add the Scrape.do plugin, and connect with an API key. Then call methods like corsair.scrapedo.api.account.asyncInfo() from your app. Corsair keeps each tenant isolated.

Yes. Scrape.do requires an API key from your Scrape.do 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 Scrape.do, GitHub, Notion, Stripe, and the rest. Trigger Scrape.do 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 Scrape.do - fetch pages as HTML, Markdown, JSON network reports or screenshots through rotating proxies, and run bulk URL jobs asynchronously. Common builds include sync jobs, admin tooling, and agents that call Scrape.do 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 Scrape.do 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/scrapedo in the open repo. When Scrape.do 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 Scrape.do data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Scrape.do 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 Scrape.do on a link in Strict mode and every write waits for your approval, while destructive actions are refused. None of the Scrape.do operations are destructive, so the default Cautious mode runs them all without asking. You can change a link's mode at hub.corsair.dev/me.