Ragic for AI agents
Ragic is a web-based database builder that lets users create and manage databases as easily as a spreadsheet. Small businesses use it to build custom record-keeping tools without code. 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 Ragic.
Search records in a sheet
Search for entries matching a value before updating or exporting them.
Download a record as PDF
Export a specific record as a formatted PDF for sharing outside the system.
Delete an entry with approval
Remove a record from the database only after the owner confirms it should be deleted.
7 Ragic actions, graded by risk.
Every Ragic 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.
- ragic.get_entryGet Entry
- ragic.search_recordsSearch Records
- ragic.get_record_as_pdfGet Record as PDF
- ragic.get_action_buttonsGet Action Buttons
- ragic.get_custom_print_reportGet Custom Print Report
- ragic.download_fileDownload File
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- ragic.delete_entryDelete Entry
Ragic in three steps.
- 01Your users connect RagicThey add their Ragic 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 Entry” can be denied outright.
- 03Any agent can actYour agent calls Ragic through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('ragic', { read: 'allow', write: 'ask', destructive: 'deny', // delete_entry }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Ragic connects.
Users add their Ragic 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 Ragic 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 Ragic from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore databases and spreadsheets apps.
Ragic and Arc0, answered.
Can I use Ragic with Claude, ChatGPT or Cursor?
Yes. Connect Ragic 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 Ragic actions you allow.
How do users connect Ragic?
Users add their Ragic 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 Ragic actions can my agent take?
7 in total: 6 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 Ragic?
Yes. Actions like “delete Entry” 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 Ragic too?
Yes. The same Ragic connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Ragic into your agent.
Your users connect Ragic 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