Diffbot Article API
Diffbot Article API analyzes a webpage URL and returns structured article content, title, author, text, HTML, dates, images, and metadata. It is designed for URL-to-structured-text extraction rather than browser automation.
Connect this API to an AI agent Browse all specs
What you can do with Diffbot Article API via MCP
Every endpoint below becomes a governed tool your AI agent (Claude, ChatGPT, or a customer-facing VX agent) can call — with scoped permissions, sandbox testing, and audit logs.
| Method | Path | Operation | Description |
|---|---|---|---|
| GET | /article |
getArticle | Extract an article Method: GET Path: /article IMPORTANT: This function has 2 REQUIRED parameter(s) and 3 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Query Parameters: REQUIRED: - token: Diffbot API token. - url: Absolute article or webpage URL to analyze. OPTIONAL: - fields: Comma-separated fields to return. - discussion: Extract discussion/comment data when supported. - timeout: Request timeout in milliseconds. |
Usage guide
## Authentication Create a Diffbot API token in the Diffbot dashboard. Pass it as the required `token` query parameter on each request. Keep the token in a server-side secret store and do not expose it in client-side applications. ## Operation `GET /article` accepts the target `url` and returns structured article data. The response can include normalized text, HTML, title, author, publication date, images, and metadata. Use `fields` to control the returned fields where supported. ## Example ```bash curl -G "https://api.diffbot.com/v3/article" \ --data-urlencode "token=$DIFFBOT_TOKEN" \ --data-urlencode "url=https://example.com/article" ``` Official documentation: https://www.diffbot.com/docs/extract/article
How to use this spec
- Create a free VX Agents account (sandbox tools included).
- Open the marketplace and connect “Diffbot Article API” to an agent.
- Expose it as an MCP server for Claude/ChatGPT, or chat with it directly.