API Labz for AI agents
API Labz bundles a set of small AI-driven utility endpoints, from data validation to searching other tools, for developers who want quick building blocks without integrating each service separately. 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 API Labz.
Validate a bank account number
Check whether an IBAN is correctly formatted before using it in a payment.
Search Trello with natural language
Run an AI-powered search across a Trello board to find a specific card.
List Airtable tables before syncing data
List the tables in an Airtable base to confirm the target before writing records.
4 API Labz actions, graded by risk.
Every API Labz action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- api_labz.list_tablesList Airtable Tables
write
3Create and change things. Allow, or ask the user first.
- api_labz.iban_validatorValidate IBAN
- api_labz.integrate_dealIntegrate Deal
- api_labz.trello_ai_search_engineTrello AI Search Engine
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
API Labz in three steps.
- 01Your users connect API LabzThey add their API Labz api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “validate IBAN” can wait for the user to approve.
- 03Any agent can actYour agent calls API Labz through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('api_labz', { read: 'allow', write: 'ask', // iban_validator destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How API Labz connects.
Users add their API Labz 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 API Labz 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 API Labz from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
API Labz and Arc0, answered.
Can I use API Labz with Claude, ChatGPT or Cursor?
Yes. Connect API Labz 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 API Labz actions you allow.
How do users connect API Labz?
Users add their API Labz 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 API Labz actions can my agent take?
4 in total: 1 read, 3 write and 0 destructive, such as “validate IBAN”. Your policies decide which of them each agent may call.
Can I make my agent read-only in API Labz?
Yes. Allow read actions and deny writes in the API Labz policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call API Labz too?
Yes. The same API Labz connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug API Labz into your agent.
Your users connect API Labz once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan