Documentero for AI agents
Documentero generates Word, PDF, and Excel documents from reusable templates and structured input data, helping operations teams turn spreadsheet rows into finished, branded documents automatically. 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 Documentero.
Generate a document from data
Generate a filled document from a template and a record's data when a request comes in.
Check a template's schema
Read a template's JSON schema to confirm which fields it expects before mapping data to it.
Review templates before choosing one
List available templates as a read-only step before selecting the right one for a document type.
4 Documentero actions, graded by risk.
Every Documentero 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.
- documentero.list_templatesList Templates
- documentero.get_template_metadataGet Template Metadata
- documentero.get_template_json_schemaGet Template JSON Schema
write
1Create and change things. Allow, or ask the user first.
- documentero.generate_documentGenerate Document
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Documentero in three steps.
- 01Your users connect DocumenteroThey add their Documentero api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “generate Document” can wait for the user to approve.
- 03Any agent can actYour agent calls Documentero through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('documentero', { read: 'allow', write: 'ask', // generate_document destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Documentero connects.
Users add their Documentero 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 Documentero 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 Documentero from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Documentero and Arc0, answered.
Can I use Documentero with Claude, ChatGPT or Cursor?
Yes. Connect Documentero 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 Documentero actions you allow.
How do users connect Documentero?
Users add their Documentero 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 Documentero actions can my agent take?
4 in total: 3 read, 1 write and 0 destructive, such as “generate Document”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Documentero?
Yes. Allow read actions and deny writes in the Documentero policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Documentero too?
Yes. The same Documentero connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Documentero into your agent.
Your users connect Documentero 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