Jentic for AI agents
Jentic lets agents search, load, and execute operations across a managed catalog of third-party APIs while credentials stay in Jentic's vault. 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 Jentic.
Search for an API operation
Search the catalog for an API operation that matches a task, like sending an SMS.
Load execution details for an operation
Load the parameters an API operation needs before it is executed on a user's behalf.
Execute an approved operation
Execute a found API operation only after the user confirms the specific action it will take.
4 Jentic actions, graded by risk.
Every Jentic 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.
- jentic.search_apisSearch apis
- jentic.list_credentialsList credentials
write
2Create and change things. Allow, or ask the user first.
- jentic.executeExecute
- jentic.load_execution_infoLoad execution info
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Jentic in three steps.
- 01Your users connect JenticThey sign in to Jentic on Arc0 Connect, under your brand, and approve the access you ask for.
- 02You set the rulesReads run, and writes like “execute” can wait for the user to approve.
- 03Any agent can actYour agent calls Jentic through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('jentic', { read: 'allow', write: 'ask', // execute destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Jentic connects.
Jentic runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Jentic through the same endpoint, policies and audit log as every other app.
The same Jentic 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
- OAuth 2.0 (MCP)
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Jentic from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Jentic and Arc0, answered.
Can I use Jentic with Claude, ChatGPT or Cursor?
Yes. Connect Jentic 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 Jentic actions you allow.
How do users connect Jentic?
Jentic runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Jentic through the same endpoint, policies and audit log as every other app.
Which Jentic actions can my agent take?
4 in total: 2 read, 2 write and 0 destructive, such as “execute”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Jentic?
Yes. Allow read actions and deny writes in the Jentic policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Jentic too?
Yes. The same Jentic connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Jentic into your agent.
Your users connect Jentic 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