Didit for AI agents

Didit provides identity verification and compliance APIs, covering KYC, KYB, and anti-money-laundering checks for onboarding and ongoing risk reviews, used by fintechs and marketplaces vetting new customers. 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.

Security and identityAPI keyMCP + RESTdidit.me
AUDIT LOG · DIDITPOLICY: acme-support
09:41:07 · claude · u_8f2read
didit.list_users
List Users✓ allowed · 212ms
09:41:08 · claude · u_8f2read
didit.get_user
Get User✓ allowed · 164ms
09:41:09 · claude · u_8f2write
didit.create_verification_session
Create Verification Session✓ approved · approved by user
EVERY DIDIT CALL, ON THE RECORD
01 · USE CASES

What agents do in Didit.

01

Check a verification decision

Pull the outcome of an identity verification session before approving a new account.

02

Start a new verification session

Create a verification session for a customer once they submit their onboarding documents.

03

Read balance before billing questions

Check the billing balance as a read-only step when finance asks about verification credit usage.

02 · ACTIONS

10 Didit actions, graded by risk.

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

read

9

Look things up. Allowed by default.

  • didit.get_user
    Get User
  • didit.list_users
    List Users
  • didit.get_business
    Get Business
  • didit.get_workflow
    Get Workflow
  • didit.list_workflows
    List Workflows
  • didit.list_businesses
    List Businesses
  • didit.get_billing_balance
    Get Billing Balance
  • didit.get_verification_decision
    Get Verification Decision
  • didit.list_verification_sessions
    List Verification Sessions

write

1

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

  • didit.create_verification_session
    Create Verification Session

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Didit in three steps.

  1. 01Your users connect DiditThey add their Didit api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “create Verification Session” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Didit 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('didit', {
  read: 'allow',
  write: 'ask',        // create_verification_session
  destructive: 'deny',  
})

# 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 Didit connects.

Users add their Didit 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 Didit 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 Didit from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Didit and Arc0, answered.

Q01

Can I use Didit with Claude, ChatGPT or Cursor?

Yes. Connect Didit 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 Didit actions you allow.

Q02

How do users connect Didit?

Users add their Didit 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 Didit actions can my agent take?

10 in total: 9 read, 1 write and 0 destructive, such as “create Verification Session”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Didit?

Yes. Allow read actions and deny writes in the Didit policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Didit too?

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

Get started

Plug Didit into your agent.

Your users connect Didit once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

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