---
title: "Diffbot integration for LuumenAI"
url: "https://www.luumen.ai/integrations/diffbot/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Diffbot integration for LuumenAI

Pull structured data off web pages, and run bulk extract jobs from the terminal

## What LuumenAI can do with Diffbot

LuumenAI connects to Diffbot with an API token and exposes 35 tools (25 read-only · 6 write · 4 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: API token
- Tools available: 35 tools (25 read-only · 6 write · 4 destructive)
- Plan: available on all plans
- Category: AI & automation

## About Diffbot with LuumenAI

Connect Diffbot and Luumen can read page structure, article fields, list pages, and job posting data without leaving the terminal. It can also check your credit balance and the state of any bulk job. When you need to process a list of URLs, Luumen prepares the bulk extract job and shows you the parameters before anything runs.

## Example tools

Read-only (25 in total):

- `DIFFBOT_COMBINE_ENTITY_PROFILES` — Combine multiple entity profiles into a unified view using the Diffbot Knowledge Graph.
- `DIFFBOT_DOWNLOAD_BULK_RESULTS` — Download results of a bulk enhance job with filtering options via POST request.
- `DIFFBOT_ENHANCE_ENTITY` — Enrich a person or organization with comprehensive data from the Diffbot Knowledge Graph.
- `DIFFBOT_EXTRACT_JOB` — Extract structured job posting data from job listing pages.
- `DIFFBOT_EXTRACT_LIST` — Extract structured data from list-style pages like news indexes, product listings, and directory pages.
- `DIFFBOT_GET_ACCOUNT` — Retrieves comprehensive Diffbot account information including subscription plan details, credit balance, usage history, and account status.
- `DIFFBOT_GET_ANALYZE` — Automatically analyzes a web page to determine its type and extract structured data.
- `DIFFBOT_GET_ARTICLE` — Extract information from articles, including authors, publication dates, and images.

Write and destructive (10 in total, approval required by default):

- `DIFFBOT_CREATE_BULK` — Submit a bulk extract job to process multiple URLs with Extract APIs.
- `DIFFBOT_CREATE_CUSTOM_API` — Create or update the parameters and ruleset of a Custom API.
- `DIFFBOT_CREATE_KG_BULK_ENHANCE` — Submit a bulk enhance job to enrich multiple entities asynchronously.
- `DIFFBOT_DELETE_CUSTOM_API` — Delete custom API definitions for a given URL pattern.
- `DIFFBOT_DELETE_KG_ENHANCE_BULKJOB` — Delete an Enhance Bulkjob.
- `DIFFBOT_MANAGE_CRAWL` — Manages Diffbot crawl jobs: pause, restart, delete, or view status.
- `DIFFBOT_START_BULK` — Start a Bulk Extract job.
- `DIFFBOT_START_CRAWL` — Initiates a Diffbot crawl job that spiders a website starting from seed URLs and processes discovered pages with a specified Extract API.

## Frequently asked questions

### How does LuumenAI connect to Diffbot?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Diffbot on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 4 actions classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to Diffbot — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/diffbot/