CheckFlow for AI agents
CheckFlow turns repeatable business processes into checklists and workflows, letting a team run the same process consistently instead of relying on memory. 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 CheckFlow.
Find a running checklist
Find a checklist by name or status to see how far along a process is.
Check a task's details
Check a specific task's details within a checklist before marking it complete.
Review process analytics
Pull analytics on completed checklists to see where a process tends to slow down.
10 CheckFlow actions, graded by risk.
Every CheckFlow action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
9Look things up. Allowed by default.
- checkflow.list_tagsList Tags
- checkflow.get_analyticsGet Analytics
- checkflow.list_templatesList Templates
- checkflow.find_checklistsFind Checklists
- checkflow.get_task_detailsGet Task Details
- checkflow.get_team_directoryGet Team Directory
- checkflow.list_template_tasksList Template Tasks
- checkflow.list_checklist_detailsList Checklist Details
- checkflow.list_webhook_subscriptionsList Webhook Subscriptions
write
1Create and change things. Allow, or ask the user first.
- checkflow.create_tagCreate Tag
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
CheckFlow in three steps.
- 01Your users connect CheckFlowThey add their CheckFlow api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Tag” can wait for the user to approve.
- 03Any agent can actYour agent calls CheckFlow through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('checkflow', { read: 'allow', write: 'ask', // create_tag destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How CheckFlow connects.
Users add their CheckFlow 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 CheckFlow 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 CheckFlow from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore project management apps.
CheckFlow and Arc0, answered.
Can I use CheckFlow with Claude, ChatGPT or Cursor?
Yes. Connect CheckFlow 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 CheckFlow actions you allow.
How do users connect CheckFlow?
Users add their CheckFlow 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 CheckFlow actions can my agent take?
10 in total: 9 read, 1 write and 0 destructive, such as “create Tag”. Your policies decide which of them each agent may call.
Can I make my agent read-only in CheckFlow?
Yes. Allow read actions and deny writes in the CheckFlow policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call CheckFlow too?
Yes. The same CheckFlow connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug CheckFlow into your agent.
Your users connect CheckFlow 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