Typless for AI agents
Typless extracts structured data from documents using AI, used by operations teams automating manual data entry from paperwork. 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 Typless.
List supported document types
Check which document formats can be processed before submitting one, a read-only lookup.
Get the user's profile
Read account profile details as a read-only status check.
Update account profile details
Update a profile field only after confirming the new value with the user.
3 Typless actions, graded by risk.
Every Typless 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.
- typless.get_profileGet User Profile
- typless.get_document_typesGet Document Types
write
1Create and change things. Allow, or ask the user first.
- typless.update_profileUpdate User Profile
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Typless in three steps.
- 01Your users connect TyplessThey add their Typless api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “update User Profile” can wait for the user to approve.
- 03Any agent can actYour agent calls Typless through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('typless', { read: 'allow', write: 'ask', // update_profile destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Typless connects.
Users add their Typless 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 Typless 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 Typless from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Typless and Arc0, answered.
Can I use Typless with Claude, ChatGPT or Cursor?
Yes. Connect Typless 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 Typless actions you allow.
How do users connect Typless?
Users add their Typless 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 Typless actions can my agent take?
3 in total: 2 read, 1 write and 0 destructive, such as “update User Profile”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Typless?
Yes. Allow read actions and deny writes in the Typless policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Typless too?
Yes. The same Typless connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Typless into your agent.
Your users connect Typless 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