Get started

Parseur for AI agents

Parseur uses AI to automatically extract structured data from emails, PDFs, and other documents. Operations teams use it to turn incoming paperwork into usable data without manual entry. 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.

Connect ParseurSee the 26 actions ↓
DocumentsAPI keyMCP + RESTparseur.com
AUDIT LOG · PARSEURPOLICY: acme-support
09:41:07 · claude · u_8f2read
parseur.list_templates
List Templates for Mailbox✓ allowed · 212ms
09:41:08 · claude · u_8f2read
parseur.get_mailbox
Get Mailbox by ID✓ allowed · 164ms
09:41:09 · claude · u_8f2write
parseur.create_mailbox
Create mailbox✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
parseur.delete_mailbox
Delete mailbox✕ blocked · policy: deny
EVERY PARSEUR CALL, ON THE RECORD
01 · USE CASES

What agents do in Parseur.

01

Upload a document for parsing

Send an email or PDF document to a mailbox so it gets parsed into structured fields.

02

Check a document's parsed data

Look up a parsed document's fields read-only to verify accuracy before export.

03

Delete a mailbox with approval

Remove a mailbox and its parsing rules only after an admin confirms it is decommissioned.

02 · ACTIONS

26 Parseur actions, graded by risk.

Every Parseur action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

10

Look things up. Allowed by default.

  • parseur.get_mailbox
    Get Mailbox by ID
  • parseur.get_document
    Get Document
  • parseur.list_templates
    List Templates for Mailbox
  • parseur.list_mailboxes2
    List Mailboxes (Full Details)
  • parseur.get_document_logs
    Get Document Logs
  • parseur.get_mailbox_schema
    Get Mailbox Schema
  • parseur.get_bootstrap_config
    Get Bootstrap Config
  • parseur.list_custom_downloads
    List Custom Downloads
  • parseur.list_documents_in_mailbox
    List Documents in Mailbox
  • parseur.retrieve_webhook
    Retrieve a webhook

write

11

Create and change things. Allow, or ask the user first.

  • parseur.create_mailbox
    Create mailbox
  • parseur.update_mailbox
    Update Mailbox
  • parseur.update_webhook
    Update webhook
  • parseur.create_custom_download
    Create custom download
  • parseur.update_custom_download
    Update custom download
  • parseur.copy_mailbox
    Copy Mailbox
  • parseur.copy_document
    Copy Document
  • parseur.skip_document
    Skip a document
  • parseur.enable_webhook
    Enable webhook
  • parseur.reprocess_document
    Reprocess a document
  • parseur.upload_email_document
    Upload Email Document

destructive

5

Delete, cancel or archive. Ask first, or deny outright.

  • parseur.delete_mailbox
    Delete mailbox
  • parseur.delete_webhook
    Delete webhook
  • parseur.delete_document
    Delete document
  • parseur.delete_custom_download
    Delete custom download
  • parseur.disable_webhook
    Disable webhook
03 · HOW IT WORKS

Parseur in three steps.

  1. 01Your users connect ParseurThey add their Parseur api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create mailbox” can wait for the user, and “delete mailbox” can be denied outright.
  3. 03Any agent can actYour agent calls Parseur through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('parseur', {
  read: 'allow',
  write: 'ask',        // create_mailbox
  destructive: 'deny',  // delete_mailbox
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Parseur connects.

Users add their Parseur 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 Parseur 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
05 · WORKS WITH

Use Parseur from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More documents apps.

Google Docs43 actionsActiveMerge13 actionsAirparser10 actionsAlgodocs3 actionsDocuSign338 actionsSharePoint Graph162 actionsSharePoint105 actionsDocumenso77 actions
ALL DOCUMENTS APPS →
07 · FAQ

Parseur and Arc0, answered.

Q01

Can I use Parseur with Claude, ChatGPT or Cursor?

Yes. Connect Parseur 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 Parseur actions you allow.

Q02

How do users connect Parseur?

Users add their Parseur 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.

Q03

Which Parseur actions can my agent take?

26 in total: 10 read, 11 write and 5 destructive, such as “create mailbox”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Parseur?

Yes. Actions like “delete mailbox” 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.

Q05

Can my own backend call Parseur too?

Yes. The same Parseur connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Parseur into your agent.

Your users connect Parseur once, under your brand. Your agent gets 26 actions behind your policies, with every call on the record.

Connect ParseurBrowse all apps →

Free to build · MCP + REST · Audit log on every plan