Starton for AI agents
Starton is a Web3 developer platform for deploying and interacting with smart contracts, storing files on IPFS, and monitoring blockchain events through one API. 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 Starton.
Look up deployed smart contracts
List the smart contracts registered on an account so a developer can confirm which ones are already live.
Upload files to IPFS storage
Store a file on IPFS and return its hash after a user approves the upload for a project.
Remove a stale event watcher
Delete a smart contract event watcher only after confirming with the user that it is no longer needed.
6 Starton actions, graded by risk.
Every Starton action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- starton.get_watcherGet Watcher
- starton.get_webhooksGet Webhooks
- starton.get_templatesGet Templates
- starton.get_smart_contractsGet Smart Contracts
write
1Create and change things. Allow, or ask the user first.
- starton.upload_fileUpload File to IPFS
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- starton.delete_smart_contract_eventDelete Smart Contract Event
Starton in three steps.
- 01Your users connect StartonThey add their Starton api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “upload File to IPFS” can wait for the user, and “delete Smart Contract Event” can be denied outright.
- 03Any agent can actYour agent calls Starton through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('starton', { read: 'allow', write: 'ask', // upload_file destructive: 'deny', // delete_smart_contract_event }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Starton connects.
Users add their Starton 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 Starton 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 Starton from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Starton and Arc0, answered.
Can I use Starton with Claude, ChatGPT or Cursor?
Yes. Connect Starton 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 Starton actions you allow.
How do users connect Starton?
Users add their Starton 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 Starton actions can my agent take?
6 in total: 4 read, 1 write and 1 destructive, such as “upload File to IPFS”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Starton?
Yes. Actions like “delete Smart Contract Event” 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.
Can my own backend call Starton too?
Yes. The same Starton connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Starton into your agent.
Your users connect Starton once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan