Get started

Triggercmd for AI agents

TRIGGERcmd runs pre-configured commands on remote computers, used by people who need to trigger scripts or actions on a machine they aren't physically at. 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 TriggercmdSee the 5 actions ↓
Developer toolsAPI keyMCP + RESTtriggercmd.com
AUDIT LOG · TRIGGERCMDPOLICY: acme-support
09:41:07 · claude · u_8f2read
triggercmd.list_computers
List TriggerCMD Computers✓ allowed · 212ms
09:41:08 · claude · u_8f2read
triggercmd.list_commands_v2
List TriggerCMD Commands V2✓ allowed · 164ms
09:41:09 · claude · u_8f2write
triggercmd.trigger_command
Trigger Command✓ approved · approved by user
EVERY TRIGGERCMD CALL, ON THE RECORD
01 · USE CASES

What agents do in Triggercmd.

01

List available commands

Pull the commands configured on a computer as a read-only check before running one.

02

Confirm before triggering a command

Get approval before running a command on a remote computer, since it executes immediately on that machine.

03

List connected computers

Read which computers are currently online and available to receive commands.

02 · ACTIONS

5 Triggercmd actions, graded by risk.

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

read

3

Look things up. Allowed by default.

  • triggercmd.list_computers
    List TriggerCMD Computers
  • triggercmd.list_commands_v2
    List TriggerCMD Commands V2
  • triggercmd.list_panel_buttons
    List TriggerCMD Panel Buttons

write

2

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

  • triggercmd.trigger_command
    Trigger Command
  • triggercmd.trigger_panel_button
    Trigger Panel Button

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Triggercmd in three steps.

  1. 01Your users connect TriggercmdThey add their Triggercmd api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “trigger Command” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Triggercmd 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('triggercmd', {
  read: 'allow',
  write: 'ask',        // trigger_command
  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 Triggercmd connects.

Users add their Triggercmd 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 Triggercmd 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 Triggercmd from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More developer tools apps.

GitHub896 actionsSupabase129 actions0CodeKit8 actionsAbly25 actionsAbstract3 actionsAddressfinder17 actionsAddresszen2 actionsAlchemy36 actions
ALL DEVELOPER TOOLS APPS →
07 · FAQ

Triggercmd and Arc0, answered.

Q01

Can I use Triggercmd with Claude, ChatGPT or Cursor?

Yes. Connect Triggercmd 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 Triggercmd actions you allow.

Q02

How do users connect Triggercmd?

Users add their Triggercmd 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 Triggercmd actions can my agent take?

5 in total: 3 read, 2 write and 0 destructive, such as “trigger Command”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Triggercmd?

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

Q05

Can my own backend call Triggercmd too?

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

Get started

Plug Triggercmd into your agent.

Your users connect Triggercmd once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.

Connect TriggercmdBrowse all apps →

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