Trigger.dev for AI agents
Trigger.dev is a platform for running background tasks and workflows reliably, used by developers who need scheduled or event-driven jobs without managing their own queue. 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 Trigger.dev.
Trigger a background task
Kick off a defined task run with its input parameters.
Check a run's result
Look up whether a task run succeeded and read its output, a read-only check.
List recent errors
Pull recent task errors to see what's failing before retrying anything.
10 Trigger.dev actions, graded by risk.
Every Trigger.dev action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- trigger_dev.get_runGet Run
- trigger_dev.get_batchGet Batch
- trigger_dev.get_errorGet Error
- trigger_dev.list_runsList Runs
- trigger_dev.list_errorsList Errors
- trigger_dev.get_run_resultGet Run Result
- trigger_dev.get_batch_resultsGet Batch Results
write
3Create and change things. Allow, or ask the user first.
- trigger_dev.trigger_taskTrigger Task
- trigger_dev.batch_trigger_taskBatch Trigger Task
- trigger_dev.execute_trql_queryExecute TRQL Query
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Trigger.dev in three steps.
- 01Your users connect Trigger.devThey add their Trigger.dev api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “trigger Task” can wait for the user to approve.
- 03Any agent can actYour agent calls Trigger.dev through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('trigger_dev', { read: 'allow', write: 'ask', // trigger_task destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Trigger.dev connects.
Users add their Trigger.dev 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 Trigger.dev 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 Trigger.dev from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Trigger.dev and Arc0, answered.
Can I use Trigger.dev with Claude, ChatGPT or Cursor?
Yes. Connect Trigger.dev 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 Trigger.dev actions you allow.
How do users connect Trigger.dev?
Users add their Trigger.dev 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 Trigger.dev actions can my agent take?
10 in total: 7 read, 3 write and 0 destructive, such as “trigger Task”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Trigger.dev?
Yes. Allow read actions and deny writes in the Trigger.dev policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Trigger.dev too?
Yes. The same Trigger.dev connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Trigger.dev into your agent.
Your users connect Trigger.dev 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