Get started

Fluxguard for AI agents

Fluxguard is an AI-powered website change detection tool that monitors pages and alerts teams to meaningful content changes, used by legal, compliance, and competitive intelligence teams. 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 FluxguardSee the 13 actions ↓
DevOps and monitoringAPI keyMCP + RESTfluxguard.com
AUDIT LOG · FLUXGUARDPOLICY: acme-support
09:41:07 · claude · u_8f2read
fluxguard.get_user
Get Current FluxGuard Account✓ allowed · 212ms
09:41:08 · claude · u_8f2read
fluxguard.get_webhooks
Get FluxGuard Webhooks✓ allowed · 164ms
09:41:09 · claude · u_8f2write
fluxguard.create_webhook
Create Webhook✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
fluxguard.delete_page
Delete Fluxguard Page✕ blocked · policy: deny
EVERY FLUXGUARD CALL, ON THE RECORD
01 · USE CASES

What agents do in Fluxguard.

01

Check a monitored page's changes

Get a page's tracked data to see what changed since the last crawl.

02

Start a new crawl

Initiate a crawl on a site once a new page needs to be added to monitoring.

03

Confirm before deleting a site

Require approval before deleting a monitored site, since it removes every page tracked under it.

02 · ACTIONS

13 Fluxguard actions, graded by risk.

Every Fluxguard 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.

  • fluxguard.get_user
    Get Current FluxGuard Account
  • fluxguard.get_webhooks
    Get FluxGuard Webhooks
  • fluxguard.get_page_data
    Get FluxGuard Page Data
  • fluxguard.get_all_categories
    Get All FluxGuard Categories
  • fluxguard.get_sample_webhook
    Get Sample Webhook Payload

write

5

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

  • fluxguard.add_page
    Add FluxGuard Page
  • fluxguard.create_webhook
    Create Webhook
  • fluxguard.create_site_category
    Create FluxGuard Site Category
  • fluxguard.initiate_crawl
    Initiate FluxGuard Crawl
  • fluxguard.webhook_notification
    Fluxguard Webhook Notification

destructive

3

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

  • fluxguard.delete_page
    Delete Fluxguard Page
  • fluxguard.delete_site
    Delete Fluxguard Site
  • fluxguard.delete_webhook
    Delete Webhook
03 · HOW IT WORKS

Fluxguard in three steps.

  1. 01Your users connect FluxguardThey add their Fluxguard api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Webhook” can wait for the user, and “delete Fluxguard Page” can be denied outright.
  3. 03Any agent can actYour agent calls Fluxguard 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('fluxguard', {
  read: 'allow',
  write: 'ask',        // create_webhook
  destructive: 'deny',  // delete_page
})

# 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 Fluxguard connects.

Users add their Fluxguard 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 Fluxguard 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 Fluxguard from any agent.

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

More devops and monitoring apps.

PagerDuty368 actionsServiceNow171 actionsNew Relic159 actionsGrafana Cloud118 actionsBetter Stack117 actionsDatadog65 actionsMezmo36 actionsStatuscake30 actions
ALL DEVOPS AND MONITORING APPS →
07 · FAQ

Fluxguard and Arc0, answered.

Q01

Can I use Fluxguard with Claude, ChatGPT or Cursor?

Yes. Connect Fluxguard 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 Fluxguard actions you allow.

Q02

How do users connect Fluxguard?

Users add their Fluxguard 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 Fluxguard actions can my agent take?

13 in total: 5 read, 5 write and 3 destructive, such as “create Webhook”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Fluxguard?

Yes. Actions like “delete Fluxguard Page” 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 Fluxguard too?

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

Get started

Plug Fluxguard into your agent.

Your users connect Fluxguard once, under your brand. Your agent gets 13 actions behind your policies, with every call on the record.

Connect FluxguardBrowse all apps →

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