DirectIQ for AI agents
DirectIQ sends transactional email through a dashboard and API, giving developers a simple way to trigger one-off messages like receipts, password resets, and account notifications. 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 DirectIQ.
Send a transactional email
Send a receipt or notification email to a customer right after an order or account event.
Confirm recipient before sending
Have an agent confirm the recipient address and template before a transactional send goes out.
Log every send in the audit trail
Record each transactional email sent through Arc0 so support can trace what went to a customer and when.
1 DirectIQ actions, graded by risk.
Every DirectIQ action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
1Create and change things. Allow, or ask the user first.
- directiq.send_transactional_emailSend Transactional Email
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
DirectIQ in three steps.
- 01Your users connect DirectIQThey add their DirectIQ api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “send Transactional Email” can wait for the user to approve.
- 03Any agent can actYour agent calls DirectIQ through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('directiq', { read: 'allow', write: 'ask', // send_transactional_email destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How DirectIQ connects.
Users add their DirectIQ 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 DirectIQ 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 DirectIQ from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
DirectIQ and Arc0, answered.
Can I use DirectIQ with Claude, ChatGPT or Cursor?
Yes. Connect DirectIQ 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 DirectIQ actions you allow.
How do users connect DirectIQ?
Users add their DirectIQ 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 DirectIQ actions can my agent take?
1 in total: 0 read, 1 write and 0 destructive, such as “send Transactional Email”. Your policies decide which of them each agent may call.
Can I make my agent read-only in DirectIQ?
Yes. Allow read actions and deny writes in the DirectIQ policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call DirectIQ too?
Yes. The same DirectIQ connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug DirectIQ into your agent.
Your users connect DirectIQ once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan