Get started

Identitycheck for AI agents

IdentityCheck verifies user identities using algorithms and data sources to reduce fraud and confirm accurate onboarding. Security and IT teams use it as one signal among several in a broader risk review. 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 IdentitycheckSee the 11 actions ↓
Security and identityAPI keyMCP + RESTidentitycheck.com
AUDIT LOG · IDENTITYCHECKPOLICY: acme-support
09:41:07 · claude · u_8f2read
identitycheck.get_document_content
Get Document Content✓ allowed · 212ms
09:41:08 · claude · u_8f2read
identitycheck.check_api_health
Check API Health✓ allowed · 164ms
09:41:09 · claude · u_8f2write
identitycheck.update_configuration
Update Configuration✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
identitycheck.delete_configuration
Delete configuration✕ blocked · policy: deny
EVERY IDENTITYCHECK CALL, ON THE RECORD
01 · USE CASES

What agents do in Identitycheck.

01

Check an onboarding status

Check the verification status of a customer's identity onboarding before granting account access.

02

Pull a submitted document

Retrieve the content of a submitted ID document for a compliance review.

03

Update configuration with approval

Update a verification configuration only after the compliance team confirms the new rule.

02 · ACTIONS

11 Identitycheck actions, graded by risk.

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

read

8

Look things up. Allowed by default.

  • identitycheck.get_document_content
    Get Document Content
  • identitycheck.check_api_health
    Check API Health
  • identitycheck.fetch_onboardings
    Fetch Onboardings
  • identitycheck.fetch_configuration
    Fetch Configuration
  • identitycheck.fetch_all_configurations
    Fetch All Configurations
  • identitycheck.retrieve_onboarding_status
    Retrieve Onboarding Status
  • identitycheck.fetch_notification_endpoint
    Fetch Notification Endpoint
  • identitycheck.fetch_all_notification_endpoints
    Fetch all notification endpoints

write

1

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

  • identitycheck.update_configuration
    Update Configuration

destructive

2

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

  • identitycheck.delete_configuration
    Delete configuration
  • identitycheck.delete_notification_endpoint
    Delete Notification Endpoint
03 · HOW IT WORKS

Identitycheck in three steps.

  1. 01Your users connect IdentitycheckThey add their Identitycheck api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “update Configuration” can wait for the user, and “delete configuration” can be denied outright.
  3. 03Any agent can actYour agent calls Identitycheck 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('identitycheck', {
  read: 'allow',
  write: 'ask',        // update_configuration
  destructive: 'deny',  // delete_configuration
})

# 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 Identitycheck connects.

Users add their Identitycheck 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 Identitycheck 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 Identitycheck from any agent.

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

More security and identity apps.

1Password6 actionsAbuseIPDB6 actionsAnonyflow5 actionsDnsfilter170 actionsBorneo153 actionsDigicert101 actionsParadym69 actionsPersona69 actions
ALL SECURITY AND IDENTITY APPS →
07 · FAQ

Identitycheck and Arc0, answered.

Q01

Can I use Identitycheck with Claude, ChatGPT or Cursor?

Yes. Connect Identitycheck 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 Identitycheck actions you allow.

Q02

How do users connect Identitycheck?

Users add their Identitycheck 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 Identitycheck actions can my agent take?

11 in total: 8 read, 1 write and 2 destructive, such as “update Configuration”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Identitycheck?

Yes. Actions like “delete configuration” 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 Identitycheck too?

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

Get started

Plug Identitycheck into your agent.

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

Connect IdentitycheckBrowse all apps →

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