ApptiveGrid for AI agents
ApptiveGrid is a collaborative no-code database platform for organizing records into grids and forms, used by teams to build lightweight apps without a developer. 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 ApptiveGrid.
Add a record to a grid
Create a new record in a specific grid inside a shared space.
Look up a record before editing it
Get a record by ID to confirm its current values before making a change.
Find the right grid before adding data
List spaces and grids to locate where a record belongs before creating it.
7 ApptiveGrid actions, graded by risk.
Every ApptiveGrid action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- apptivegrid.get_gridGet Grid
- apptivegrid.get_spaceGet Space
- apptivegrid.get_recordGet Record
- apptivegrid.list_spacesList Spaces
- apptivegrid.list_recordsList Records
- apptivegrid.get_current_userGet Current User
write
1Create and change things. Allow, or ask the user first.
- apptivegrid.create_recordCreate Record
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
ApptiveGrid in three steps.
- 01Your users connect ApptiveGridThey add their ApptiveGrid api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Record” can wait for the user to approve.
- 03Any agent can actYour agent calls ApptiveGrid through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('apptivegrid', { read: 'allow', write: 'ask', // create_record destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How ApptiveGrid connects.
Users add their ApptiveGrid 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 ApptiveGrid 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 ApptiveGrid from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore databases and spreadsheets apps.
ApptiveGrid and Arc0, answered.
Can I use ApptiveGrid with Claude, ChatGPT or Cursor?
Yes. Connect ApptiveGrid 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 ApptiveGrid actions you allow.
How do users connect ApptiveGrid?
Users add their ApptiveGrid 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 ApptiveGrid actions can my agent take?
7 in total: 6 read, 1 write and 0 destructive, such as “create Record”. Your policies decide which of them each agent may call.
Can I make my agent read-only in ApptiveGrid?
Yes. Allow read actions and deny writes in the ApptiveGrid policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call ApptiveGrid too?
Yes. The same ApptiveGrid connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug ApptiveGrid into your agent.
Your users connect ApptiveGrid once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan