Get started

LLMWhisperer for AI agents

LLMWhisperer converts complex documents like PDFs and scans into clean text formatted for large language models to read accurately, preserving layout and structure. 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 LLMWhispererSee the 11 actions ↓
DocumentsAPI keyMCP + RESTunstract.com
AUDIT LOG · LLMWHISPERERPOLICY: acme-support
09:41:07 · claude · u_8f2read
llmwhisperer.get_highlights
Get Highlights Metadata✓ allowed · 212ms
09:41:08 · claude · u_8f2read
llmwhisperer.convert_document_to_text_v2
Convert Document to Text (v2)✓ allowed · 164ms
09:41:09 · claude · u_8f2write
llmwhisperer.usage_get_info
Get Usage Information✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
llmwhisperer.webhook_delete
Delete Webhook✕ blocked · policy: deny
EVERY LLMWHISPERER CALL, ON THE RECORD
01 · USE CASES

What agents do in LLMWhisperer.

01

Convert a document to text

Convert an uploaded PDF into structured text so its content can be processed by a model.

02

Check a conversion's status

Look up whether a submitted document conversion has finished before pulling its extracted text, a read-only status check.

03

Pull usage statistics

Check account usage against plan limits before submitting a large batch of documents.

02 · ACTIONS

11 LLMWhisperer actions, graded by risk.

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

read

2

Look things up. Allowed by default.

  • llmwhisperer.get_highlights
    Get Highlights Metadata
  • llmwhisperer.convert_document_to_text_v2
    Convert Document to Text (v2)

write

8

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

  • llmwhisperer.usage_get_info
    Get Usage Information
  • llmwhisperer.webhook_update
    Update Webhook Configuration
  • llmwhisperer.usage_get_stats
    Get Usage Statistics
  • llmwhisperer.register_webhook
    Register Webhook
  • llmwhisperer.whisper_get_detail
    Get Whisper Detail
  • llmwhisperer.webhook_get_details
    Get Webhook Details
  • llmwhisperer.whisper_check_status
    Check Whisper Status
  • llmwhisperer.whisper_retrieve_text
    Retrieve Whisper Text

destructive

1

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

  • llmwhisperer.webhook_delete
    Delete Webhook
03 · HOW IT WORKS

LLMWhisperer in three steps.

  1. 01Your users connect LLMWhispererThey add their LLMWhisperer api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “get Usage Information” can wait for the user, and “delete Webhook” can be denied outright.
  3. 03Any agent can actYour agent calls LLMWhisperer 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('llmwhisperer', {
  read: 'allow',
  write: 'ask',        // usage_get_info
  destructive: 'deny',  // webhook_delete
})

# 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 LLMWhisperer connects.

Users add their LLMWhisperer 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 LLMWhisperer 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 LLMWhisperer 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

LLMWhisperer and Arc0, answered.

Q01

Can I use LLMWhisperer with Claude, ChatGPT or Cursor?

Yes. Connect LLMWhisperer 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 LLMWhisperer actions you allow.

Q02

How do users connect LLMWhisperer?

Users add their LLMWhisperer 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 LLMWhisperer actions can my agent take?

11 in total: 2 read, 8 write and 1 destructive, such as “get Usage Information”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in LLMWhisperer?

Yes. Actions like “delete Webhook” 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 LLMWhisperer too?

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

Get started

Plug LLMWhisperer into your agent.

Your users connect LLMWhisperer once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.

Connect LLMWhispererBrowse all apps →

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