Get started

Diffbot for AI agents

Diffbot uses AI to extract structured data from web pages, turning articles, products, and discussions into machine-readable records for teams building search, research, and data pipelines. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect DiffbotSee the 35 actions ↓
AI and modelsAPI keyMCP + RESTdiffbot.com
AUDIT LOG · DIFFBOTPOLICY: acme-support
09:41:07 · claude · u_8f2read
diffbot.list_bulk_jobs
List Bulk Jobs✓ allowed · 212ms
09:41:08 · claude · u_8f2read
diffbot.get_event
Diffbot Get Event✓ allowed · 164ms
09:41:09 · claude · u_8f2write
diffbot.create_bulk
Create Bulk Extract Job✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
diffbot.delete_custom_api
Delete Custom API✕ blocked · policy: deny
EVERY DIFFBOT CALL, ON THE RECORD
01 · USE CASES

What agents do in Diffbot.

01

Pull structured data from a page

Extract article or product data from a URL so an agent can summarize it without manual scraping.

02

Search the knowledge graph

Run a knowledge graph search to find and link entities mentioned in a report.

03

Check a bulk job before download

Read a bulk extract job's status before pulling its results into a downstream workflow.

02 · ACTIONS

35 Diffbot actions, graded by risk.

Every Diffbot action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

23

Look things up. Allowed by default.

  • diffbot.get_event
    Diffbot Get Event
  • diffbot.get_image
    Diffbot Get Image
  • diffbot.get_video
    Get Video Data
  • diffbot.get_account
    Get Diffbot Account Details
  • diffbot.get_analyze
    Diffbot Analyze
  • diffbot.get_article
    Get Article Data
  • diffbot.get_product
    Diffbot Get Product
  • diffbot.get_bulk_data
    Get Bulk Job Data
  • diffbot.get_crawl_data
    Get Crawl Data
  • diffbot.get_discussion
    Get Discussion Thread
  • diffbot.list_bulk_jobs
    List Bulk Jobs
  • diffbot.get_bulk_results
    Get Bulk Job Results
  • diffbot.list_custom_apis
    List Custom APIs
  • diffbot.search_crawl_data
    Search Crawl Job Data
  • diffbot.get_bulk_job_status
    Get Bulk Job Status
  • diffbot.get_bulk_single_result
    Get Bulk Single Result
+ 7 MORE

write

10

Create and change things. Allow, or ask the user first.

  • diffbot.create_bulk
    Create Bulk Extract Job
  • diffbot.create_custom_api
    Create or Update Custom API
  • diffbot.create_kg_bulk_enhance
    Create Bulk Enhance Job
  • diffbot.start_bulk
    Start Bulk Job
  • diffbot.start_crawl
    Start Crawl Job
  • diffbot.manage_crawl
    Manage Crawl Job
  • diffbot.stop_bulk_job
    Stop Bulk Job
  • diffbot.enhance_entity
    Enhance Entity with Knowledge Graph
  • diffbot.stop_kg_bulk_job_by_id
    Stop KG Bulk Job By ID
  • diffbot.combine_entity_profiles
    Combine Entity Profiles

destructive

2

Delete, cancel or archive. Ask first, or deny outright.

  • diffbot.delete_custom_api
    Delete Custom API
  • diffbot.delete_kg_enhance_bulkjob
    Delete KG Enhance Bulkjob
03 · HOW IT WORKS

Diffbot in three steps.

  1. 01Your users connect DiffbotThey add their Diffbot api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Bulk Extract Job” can wait for the user, and “delete Custom API” can be denied outright.
  3. 03Any agent can actYour agent calls Diffbot through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('diffbot', {
  read: 'allow',
  write: 'ask',        // create_bulk
  destructive: 'deny',  // delete_custom_api
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Diffbot connects.

Users add their Diffbot api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Diffbot connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Diffbot from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

Diffbot and Arc0, answered.

Q01

Can I use Diffbot with Claude, ChatGPT or Cursor?

Yes. Connect Diffbot to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Diffbot actions you allow.

Q02

How do users connect Diffbot?

Users add their Diffbot api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Diffbot actions can my agent take?

35 in total: 23 read, 10 write and 2 destructive, such as “create Bulk Extract Job”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Diffbot?

Yes. Actions like “delete Custom API” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Diffbot too?

Yes. The same Diffbot connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Diffbot into your agent.

Your users connect Diffbot once, under your brand. Your agent gets 35 actions behind your policies, with every call on the record.

Connect DiffbotBrowse all apps →

Free to build · MCP + REST · Audit log on every plan