Get started

Truvera for AI agents

Truvera issues and verifies digital credentials and identities, used by organizations that need to prove a claim, like a certification, is genuine and hasn't been tampered with. 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 TruveraSee the 15 actions ↓
Security and identityAPI keyMCP + RESTtruvera.io
AUDIT LOG · TRUVERAPOLICY: acme-support
09:41:07 · claude · u_8f2read
truvera.verify
Verify Credential or Presentation✓ allowed · 212ms
09:41:08 · claude · u_8f2read
truvera.retrieve_did
Retrieve DID Document✓ allowed · 164ms
09:41:09 · claude · u_8f2write
truvera.create_api_key
Create API Key✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
truvera.delete_tag
Delete Tag✕ blocked · policy: deny
EVERY TRUVERA CALL, ON THE RECORD
01 · USE CASES

What agents do in Truvera.

01

Verify a credential or presentation

Check whether a submitted credential is valid and hasn't been revoked, a read-only verification.

02

Retrieve a credential's details

Look up an issued credential's current status, contents, and revocation state.

03

Confirm before deleting a credential

Check with the user before deleting a credential, since that action can't be reversed.

02 · ACTIONS

15 Truvera actions, graded by risk.

Every Truvera 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.

  • truvera.verify
    Verify Credential or Presentation
  • truvera.retrieve_did
    Retrieve DID Document
  • truvera.retrieve_api_key
    Retrieve API Key
  • truvera.retrieve_webhook
    Retrieve Webhook
  • truvera.retrieve_api_keys
    Retrieve API Keys
  • truvera.retrieve_webhooks
    Retrieve Webhooks
  • truvera.retrieve_credential
    Retrieve Credential
  • truvera.retrieve_registries
    Retrieve Revocation Registries
  • truvera.retrieve_credentials
    Retrieve Credentials

write

2

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

  • truvera.create_api_key
    Create API Key
  • truvera.create_webhook
    Create Webhook

destructive

4

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

  • truvera.delete_tag
    Delete Tag
  • truvera.delete_api_key
    Delete API Key
  • truvera.delete_webhook
    Delete Webhook
  • truvera.delete_credential
    Delete Credential
03 · HOW IT WORKS

Truvera in three steps.

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

# 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 Truvera connects.

Users add their Truvera 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 Truvera 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 Truvera 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

Truvera and Arc0, answered.

Q01

Can I use Truvera with Claude, ChatGPT or Cursor?

Yes. Connect Truvera 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 Truvera actions you allow.

Q02

How do users connect Truvera?

Users add their Truvera 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 Truvera actions can my agent take?

15 in total: 9 read, 2 write and 4 destructive, such as “create API Key”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Truvera?

Yes. Actions like “delete Tag” 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 Truvera too?

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

Get started

Plug Truvera into your agent.

Your users connect Truvera once, under your brand. Your agent gets 15 actions behind your policies, with every call on the record.

Connect TruveraBrowse all apps →

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