Get started

CrowTerminal for AI agents

CrowTerminal is an AI-powered command line assistant with memory, giving developers automation and monitoring built around a persistent context of their work. 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 CrowTerminalSee the 27 actions ↓
Developer toolsAPI keyMCP + REST
AUDIT LOG · CROWTERMINALPOLICY: acme-support
09:41:07 · claude · u_8f2read
crowterminal.list_webhooks
List Webhooks✓ allowed · 212ms
09:41:08 · claude · u_8f2read
crowterminal.get_status
Get Service Status✓ allowed · 164ms
09:41:09 · claude · u_8f2write
crowterminal.create_webhook
Create Webhook✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
crowterminal.delete_webhook
Delete Webhook✕ blocked · policy: deny
EVERY CROWTERMINAL CALL, ON THE RECORD
01 · USE CASES

What agents do in CrowTerminal.

01

Check recent incidents

Check recent incidents logged on a service before deciding whether an issue is new.

02

Check a client's memory pattern

Check a stored memory pattern for a client before relying on it in an automation.

03

Confirm before validating sandbox changes

Validate proposed changes in a sandbox before they get applied to a real client.

02 · ACTIONS

27 CrowTerminal actions, graded by risk.

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

read

20

Look things up. Allowed by default.

  • crowterminal.get_status
    Get Service Status
  • crowterminal.get_uptime
    Get Uptime Data
  • crowterminal.get_incidents
    Get Recent Incidents
  • crowterminal.list_webhooks
    List Webhooks
  • crowterminal.get_data_types
    Get Data Types
  • crowterminal.get_platform_intel
    Get Platform Intelligence
  • crowterminal.get_sandbox_client
    Get Sandbox Client
  • crowterminal.get_sandbox_memory
    Get Sandbox Memory
  • crowterminal.get_status_history
    Get Status History
  • crowterminal.get_components_status
    Get Components Status
  • crowterminal.get_byok_platform_intel
    Get BYOK Platform Intelligence
  • crowterminal.get_client_memory_pattern
    Get Client Memory Pattern
  • crowterminal.get_client_memory_changelog
    Get Client Memory Changelog
  • crowterminal.compare_md
    Compare Agent Markdown
  • crowterminal.test_webhook
    Test Webhook
  • crowterminal.read_bulk_memory
    Bulk Read Memory
+ 4 MORE

write

6

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

  • crowterminal.create_webhook
    Create Webhook
  • crowterminal.update_webhook
    Update Webhook
  • crowterminal.ingest_data
    Ingest Analytics Data
  • crowterminal.register_agent
    Register Agent
  • crowterminal.ingest_bulk_data
    Bulk Ingest Analytics Data
  • crowterminal.run_sandbox_engagement_analysis
    Sandbox Engagement Analysis

destructive

1

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

  • crowterminal.delete_webhook
    Delete Webhook
03 · HOW IT WORKS

CrowTerminal in three steps.

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

# 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 CrowTerminal connects.

Users add their CrowTerminal 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 CrowTerminal 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 · Username and password
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use CrowTerminal 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

CrowTerminal and Arc0, answered.

Q01

Can I use CrowTerminal with Claude, ChatGPT or Cursor?

Yes. Connect CrowTerminal 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 CrowTerminal actions you allow.

Q02

How do users connect CrowTerminal?

Users add their CrowTerminal 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 CrowTerminal actions can my agent take?

27 in total: 20 read, 6 write and 1 destructive, such as “create Webhook”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in CrowTerminal?

Yes. Actions like “delete Webhook” 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 CrowTerminal too?

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

Get started

Plug CrowTerminal into your agent.

Your users connect CrowTerminal once, under your brand. Your agent gets 27 actions behind your policies, with every call on the record.

Connect CrowTerminalBrowse all apps →

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