Workiom for AI agents
Workiom builds custom workflows and connects apps to automate processes, used by small businesses replacing manual spreadsheet tracking with structured records. 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 Workiom.
Get records from a list
Pull records from a workflow list as a read-only status check.
Create a new record
Add a new record to a list, like a task or a customer entry.
Review lists before automating a process
Read all available lists before deciding which one an automation should update.
3 Workiom actions, graded by risk.
Every Workiom action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- workiom.get_recordsGet records
- workiom.get_all_listsGet all lists
write
1Create and change things. Allow, or ask the user first.
- workiom.create_recordCreate record
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Workiom in three steps.
- 01Your users connect WorkiomThey add their Workiom api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create record” can wait for the user to approve.
- 03Any agent can actYour agent calls Workiom through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('workiom', { read: 'allow', write: 'ask', // create_record destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Workiom connects.
Users add their Workiom 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 Workiom 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 Workiom from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Workiom and Arc0, answered.
Can I use Workiom with Claude, ChatGPT or Cursor?
Yes. Connect Workiom 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 Workiom actions you allow.
How do users connect Workiom?
Users add their Workiom 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 Workiom actions can my agent take?
3 in total: 2 read, 1 write and 0 destructive, such as “create record”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Workiom?
Yes. Allow read actions and deny writes in the Workiom policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Workiom too?
Yes. The same Workiom connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Workiom into your agent.
Your users connect Workiom once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan