Stack Ai for AI agents
Stack AI is a no-code platform for building and deploying enterprise AI workflows, connecting models, data sources, and tools without writing code. 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 Stack Ai.
List available integrations before building
List the connector types and integrations configured on an account before wiring a new workflow to one.
Check a workflow's action inputs
Get the inputs a workflow action expects, read-only, before an agent configures it correctly.
Check license status before scaling usage
Check the account's license status to confirm capacity before adding more workflows or triggers.
22 Stack Ai actions, graded by risk.
Every Stack Ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
22Look things up. Allowed by default.
- stack_ai.get_rootGet Root
- stack_ai.get_providerGet Provider Details
- stack_ai.list_permissionsList Permissions
- stack_ai.get_action_inputsGet Action Inputs
- stack_ai.get_provider_iconGet Provider Icon
- stack_ai.list_integrationsList Stack AI Integrations
- stack_ai.get_action_outputsGet Action Output Schema
- stack_ai.get_license_statusGet License Status
- stack_ai.get_trigger_inputsGet Trigger Inputs
- stack_ai.list_stackai_toolsList Stack AI Built-in Tools
- stack_ai.get_provider_actionGet Provider Action Details
- stack_ai.get_trigger_outputsGet Trigger Outputs
- stack_ai.get_provider_triggerGet Provider Trigger Details
- stack_ai.list_connector_typesList Connector Types
- stack_ai.list_stackai_actionsList Stack AI Actions
- stack_ai.list_permission_groupsList Permission Groups
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Stack Ai in three steps.
- 01Your users connect Stack AiThey add their Stack Ai api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Stack Ai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('stack_ai', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Stack Ai connects.
Users add their Stack Ai 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 Stack Ai 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 Stack Ai from any agent.
Stack Ai and Arc0, answered.
Can I use Stack Ai with Claude, ChatGPT or Cursor?
Yes. Connect Stack Ai 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 Stack Ai actions you allow.
How do users connect Stack Ai?
Users add their Stack Ai 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 Stack Ai actions can my agent take?
22 in total: 22 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Stack Ai?
Yes. Allow read actions and deny writes in the Stack Ai policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Stack Ai too?
Yes. The same Stack Ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Stack Ai into your agent.
Your users connect Stack Ai once, under your brand. Your agent gets 22 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan