← All integrations

WebScraping.AI MCP server

7 operations0 webhooks

Web scraping API that returns rendered HTML, text, or selected elements from pages, answers questions about a page, and extracts structured fields.

Try WebScraping.AI with your agent

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

Runs once, when you ask

WebScraping.AI tools and triggers

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

Scraping

  • Get HtmlRead-only

    Return the rendered HTML of a web page

    scraping.getHtml

  • Get Selected HtmlRead-only

    Return HTML matching one CSS selector

    scraping.getSelectedHtml

  • Get Selected MultipleRead-only

    Return HTML matching multiple CSS selectors

    scraping.getSelectedMultiple

  • Get TextRead-only

    Return clean text or Markdown extracted from a web page

    scraping.getText

Ai

  • Ask QuestionRead-only

    Answer a question using the content of a web page

    ai.askQuestion

  • Extract FieldsRead-only

    Extract requested fields from a web page as structured JSON

    ai.extractFields

Account

  • Get InfoRead-only

    Return account quota and credit information

    account.getInfo

Connect WebScraping.AI to Claude, ChatGPT or Cursor

  1. 1

    Connect WebScraping.AI in Corsair

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

    If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs WebScraping.AI. On a ChatGPT personal plan, connect WebScraping.AI 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. Every WebScraping.AI operation only reads data, so it runs right away in every mode.

FAQ

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

Yes. WebScraping.AI requires an API key from your WebScraping.AI 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 WebScraping.AI, GitHub, Notion, Stripe, and the rest. Trigger WebScraping.AI 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 api that returns rendered html, text, or selected elements from pages, answers questions about a page, and extracts structured fields. Common builds include sync jobs, admin tooling, and agents that call WebScraping.AI 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 WebScraping.AI 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/webscrapingai in the open repo. When WebScraping.AI 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 WebScraping.AI data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store WebScraping.AI 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 WebScraping.AI on a link in Strict mode and every write waits for your approval, while destructive actions are refused. Every WebScraping.AI operation only reads data, so there are no changes to approve today. You can change a link's mode at hub.corsair.dev/me.