Rize for AI agents
Rize is an AI-powered time tracking tool that automatically logs work sessions and surfaces productivity insights, and also supports card issuing for partners. 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.
What agents do in Rize.
Look up a cardholder
Get a cardholder's record before deciding whether to issue them a new card.
Issue a virtual card
Create a card for a cardholder after their spending limit is approved.
Confirm before opening an account
Check the cardholder and counterparty details first, then create a partner financial account only once approved.
8 Rize actions, graded by risk.
Every Rize action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- rize.get_cardholderGet Cardholder
- rize.get_virtual_card_imageGet Virtual Card Image
write
6Create and change things. Allow, or ask the user first.
- rize.create_cardCreate Card
- rize.create_userCreate User
- rize.create_api_keyCreate API Key
- rize.create_cardholderCreate Cardholder
- rize.create_counterpartyCreate a Rize counterparty
- rize.create_partner_financial_accountCreate Partner Financial Account
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Rize in three steps.
- 01Your users connect RizeThey add their Rize api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Card” can wait for the user to approve.
- 03Any agent can actYour agent calls Rize through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('rize', { read: 'allow', write: 'ask', // create_card destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Rize connects.
Users add their Rize 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 Rize 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
Use Rize from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Rize and Arc0, answered.
Can I use Rize with Claude, ChatGPT or Cursor?
Yes. Connect Rize 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 Rize actions you allow.
How do users connect Rize?
Users add their Rize 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.
Which Rize actions can my agent take?
8 in total: 2 read, 6 write and 0 destructive, such as “create Card”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Rize?
Yes. Allow read actions and deny writes in the Rize policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Rize too?
Yes. The same Rize connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Rize into your agent.
Your users connect Rize once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan