Get started

Browseai for AI agents

Browse.ai is a web scraping and monitoring service that teams use to turn websites into structured data feeds and get alerted when tracked pages change. 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 BrowseaiSee the 11 actions ↓
Web data and scrapingAPI keyMCP + RESTbrowse.ai
AUDIT LOG · BROWSEAIPOLICY: acme-support
09:41:07 · claude · u_8f2read
browseai.list_robot_webhooks
List Robot Webhooks✓ allowed · 212ms
09:41:08 · claude · u_8f2read
browseai.get_robots
Get Robots List✓ allowed · 164ms
09:41:09 · claude · u_8f2write
browseai.create_monitor
Create Monitor✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
browseai.delete_task
Delete a specific task✕ blocked · policy: deny
EVERY BROWSEAI CALL, ON THE RECORD
01 · USE CASES

What agents do in Browseai.

01

Check a monitor's latest run

Read-only lookup of a robot's task results before deciding whether the tracked page has changed.

02

Run a scraping robot

Run a configured robot against a target site after the user confirms which pages to extract.

03

Require approval before deleting a monitor

Treat deleting a monitor or task as destructive since it stops tracking a page's changes.

02 · ACTIONS

11 Browseai actions, graded by risk.

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

read

5

Look things up. Allowed by default.

  • browseai.get_robots
    Get Robots List
  • browseai.get_robot_tasks
    Get Robot Tasks
  • browseai.get_task_details
    Get Task Details
  • browseai.get_system_status
    Get System Status
  • browseai.list_robot_webhooks
    List Robot Webhooks

write

4

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

  • browseai.create_monitor
    Create Monitor
  • browseai.create_webhook
    Create Webhook
  • browseai.run_robot
    Run Robot
  • browseai.bulk_run_tasks
    Bulk Run Tasks

destructive

2

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

  • browseai.delete_task
    Delete a specific task
  • browseai.delete_monitor
    Delete a specific monitor
03 · HOW IT WORKS

Browseai in three steps.

  1. 01Your users connect BrowseaiThey add their Browseai api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Monitor” can wait for the user, and “delete a specific task” can be denied outright.
  3. 03Any agent can actYour agent calls Browseai 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('browseai', {
  read: 'allow',
  write: 'ask',        // create_monitor
  destructive: 'deny',  // delete_task
})

# 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 Browseai connects.

Users add their Browseai 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 Browseai 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 Browseai from any agent.

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

More web data and scraping apps.

Firecrawl30 actionsTavily5 actionsExa20 actionsAgentql3 actionsAgenty79 actionsAirtop10 actionsJust One API288 actionsApify183 actions
ALL WEB DATA AND SCRAPING APPS →
07 · FAQ

Browseai and Arc0, answered.

Q01

Can I use Browseai with Claude, ChatGPT or Cursor?

Yes. Connect Browseai 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 Browseai actions you allow.

Q02

How do users connect Browseai?

Users add their Browseai 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 Browseai actions can my agent take?

11 in total: 5 read, 4 write and 2 destructive, such as “create Monitor”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Browseai?

Yes. Actions like “delete a specific task” 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 Browseai too?

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

Get started

Plug Browseai into your agent.

Your users connect Browseai once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.

Connect BrowseaiBrowse all apps →

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