WebScraping.AI integration for AI agents.
WebScraping.AI integration for AI agents with secure authentication and server-side credential injection. Open Connector runs the OAuth, seals the token in an encrypted vault, and serves WebScraping.AI tools to your agent over MCP or a typed API — credentials injected server-side, every call audited, nothing leaving your infrastructure. Open source (AGPL-3.0) and self-hostable.
Real WebScraping.AI actions, managed and audited.
Your user connects WebScraping.AI once; your agent can then web scraping API to extract data from any website with one call. We handle proxies, browsers, CAPTCHAs and parsing. Get HTML, text, or AI-extracted JSON — scoped to the OAuth permissions you grant and the tool allowlist you configure. Every action is least-privilege and written to a tamper-evident audit trail.
- 1
Your user grants WebScraping.AI access once (OAuth) — the token lands in the vault.
- 2
Your agent calls a tool over MCP or the typed API; Open Connector injects the credential server-side.
- 3
Every routed call appends a hash-chained audit record — nothing leaves your infra.
Supported WebScraping.AI tools.
7 tools are generated from the published WebScraping.AI catalog. Descriptions are plain text; each action remains subject to its configured authentication and tool allowlist.
Showing 7 tools. All published catalog entries are included in this page's server-rendered HTML.
- Information about your account calls quota
- Returns information about your account, including the remaining API credits quota, the next billing cycle start time, and the remaining concurrent requests. The response is in JSON format.
- Account
- Extract structured data fields from a web page
- Returns structured data fields extracted from the webpage using an LLM model. Proxies and Chromium JavaScript rendering are used for page retrieval and processing.
- AI
- Page HTML by URL
- Returns the full HTML content of a webpage specified by the URL. The response is in plain text. Proxies and Chromium JavaScript rendering are used for page retrieval and processing.
- HTML
- Get an answer to a question about a given web page
- Returns the answer in plain text. Proxies and Chromium JavaScript rendering are used for page retrieval and processing, then the answer is extracted using an LLM model.
- AI
- HTML of a selected page area by URL and CSS selector
- Returns HTML of a selected page area by URL and CSS selector. Useful if you don't want to do the HTML parsing on your side.
- Selected HTML
- HTML of multiple page areas by URL and CSS selectors
- Returns HTML of multiple page areas by URL and CSS selectors. Useful if you don't want to do the HTML parsing on your side.
- Selected HTML
- Page text by URL (Markdown)
- Converts a webpage to clean Markdown ("URL to Markdown") - boilerplate is stripped and the document structure (headings, lists, tables, links) is preserved. Can be used to feed data to LLM models and RAG pipelines. text_format=plain (default) returns the raw Markdown; "json" and "xml" wrap the same Markdown content with the page title and description. Proxies and Chromium JavaScript rendering are used for page retrieval and processing. Returns JSON on error.
- Text
WebScraping.AI integration, answered
- How do AI agents use WebScraping.AI through Open Connector?
- Your user connects WebScraping.AI once with one of its cataloged authentication methods. Open Connector stores the credential in an encrypted vault and exposes WebScraping.AI tools to your agent over MCP or a typed API, with credentials injected server-side on each call.
- Is this a WebScraping.AI MCP server?
- Yes. Open Connector can serve WebScraping.AI as a named MCP server with a scoped allowlist and a per-user connection URL, so any MCP client can call WebScraping.AI actions with credentials injected server-side.
- Where do WebScraping.AI credentials live?
- In your own infrastructure. Open Connector keeps credentials in its own vault and injects them at call time, so they never leave your environment.
Give your agents WebScraping.AI — keep the keys.
Open source, self-hostable, with WebScraping.AI credentials that never leave your infrastructure. Run it from source today.