Docparser for AI agents

Docparser is a cloud document parsing tool that extracts structured data from PDFs and scanned files using configured parser rules. 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.

DocumentsAPI keyMCP + RESTdocparser.com
AUDIT LOG · DOCPARSERPOLICY: acme-support
09:41:07 · claude · u_8f2read
docparser.list_parsers
List Parsers✓ allowed · 212ms
09:41:08 · claude · u_8f2read
docparser.ping
Ping API✓ allowed · 164ms
EVERY DOCPARSER CALL, ON THE RECORD
01 · USE CASES

What agents do in Docparser.

01

Pull parsed results in bulk

Get results for multiple documents processed by a parser to feed into a reporting workflow.

02

Check available parser models

List the parser models set up on the account before routing a new document type to one.

03

Read-only parser inventory checks

List existing parsers as a read-only step before anyone decides whether a new one is needed.

02 · ACTIONS

4 Docparser actions, graded by risk.

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

read

4

Look things up. Allowed by default.

  • docparser.list_parsers
    List Parsers
  • docparser.get_parser_models
    Get Parser Models
  • docparser.get_multiple_document_results
    Get Multiple Document Results
  • docparser.ping
    Ping API

write

0

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

  • No write actions.

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Docparser in three steps.

  1. 01Your users connect DocparserThey add their Docparser api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Docparser 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('docparser', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# 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 Docparser connects.

Users add their Docparser 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 Docparser 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 Docparser from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Docparser and Arc0, answered.

Q01

Can I use Docparser with Claude, ChatGPT or Cursor?

Yes. Connect Docparser 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 Docparser actions you allow.

Q02

How do users connect Docparser?

Users add their Docparser 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 Docparser actions can my agent take?

4 in total: 4 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Docparser?

Yes. Allow read actions and deny writes in the Docparser policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Docparser too?

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

Get started

Plug Docparser into your agent.

Your users connect Docparser 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