Jev for AI agents
Jev is TypeSafe AI's System One API for discovering available models and evaluating structured state against them, returning scored or multiple-choice answers rather than free-form text. 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 Jev.
Evaluate a structured question
Evaluate a defined question against current state data to get a scored or choice-based answer.
List available models
List available evaluation models before choosing one for a new scoring task.
Review an evaluation result
Review a returned evaluation result, read-only, before it feeds into a downstream decision.
2 Jev actions, graded by risk.
Every Jev 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.
- jev.list_modelsList Models
write
1Create and change things. Allow, or ask the user first.
- jev.evaluate_stateEvaluate State
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Jev in three steps.
- 01Your users connect JevThey add their Jev api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “evaluate State” can wait for the user to approve.
- 03Any agent can actYour agent calls Jev through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('jev', { read: 'allow', write: 'ask', // evaluate_state destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Jev connects.
Users add their Jev 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 Jev 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 Jev from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Jev and Arc0, answered.
Can I use Jev with Claude, ChatGPT or Cursor?
Yes. Connect Jev 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 Jev actions you allow.
How do users connect Jev?
Users add their Jev 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 Jev actions can my agent take?
2 in total: 1 read, 1 write and 0 destructive, such as “evaluate State”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Jev?
Yes. Allow read actions and deny writes in the Jev policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Jev too?
Yes. The same Jev connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Jev into your agent.
Your users connect Jev once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan