Ninox for AI agents
Ninox is a low-code platform that enables users to create custom database applications tailored to their team's specific workflows and reporting needs. 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 Ninox.
List a team's databases
List the databases available to a team to find the right one for a task, read-only.
Check a team's configuration
Look up a team's details before deciding where to route a new record.
Approve before deleting a record
Require approval before deleting a record, since Ninox does not keep a built-in recovery option.
4 Ninox actions, graded by risk.
Every Ninox action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- ninox.get_teamGet Team
- ninox.list_teamsList Teams
- ninox.get_databasesGet Databases
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- ninox.delete_recordDelete Record
Ninox in three steps.
- 01Your users connect NinoxThey add their Ninox api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “updates” can wait for the user, and “delete Record” can be denied outright.
- 03Any agent can actYour agent calls Ninox through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('ninox', { read: 'allow', write: 'ask', destructive: 'deny', // delete_record }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Ninox connects.
Users add their Ninox 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 Ninox 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 Ninox from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore databases and spreadsheets apps.
Ninox and Arc0, answered.
Can I use Ninox with Claude, ChatGPT or Cursor?
Yes. Connect Ninox 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 Ninox actions you allow.
How do users connect Ninox?
Users add their Ninox 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 Ninox actions can my agent take?
4 in total: 3 read, 0 write and 1 destructive. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Ninox?
Yes. Actions like “delete Record” 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 Ninox too?
Yes. The same Ninox connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Ninox into your agent.
Your users connect Ninox 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