Happy Scribe for AI agents

Happy Scribe offers automatic and professional transcription and subtitling, converting audio and video into accurate text. Teams use it to make recorded audio and video searchable and easy to reuse. 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 Happy Scribe See the 20 actions ↓

Video and audioAPI keyMCP + RESThappyscribe.com

AUDIT LOG · HAPPY SCRIBEPOLICY: acme-support

09:41:07 · claude · u_8f2read

happy_scribe.list_transcriptions

List Transcriptions✓ allowed · 212ms

09:41:08 · claude · u_8f2read

happy_scribe.get_rate_limit

Get API Rate Limit✓ allowed · 164ms

09:41:09 · claude · u_8f2write

happy_scribe.create_subtitle

Create Subtitle✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

happy_scribe.delete_webhook

Delete Webhook✕ blocked · policy: deny

EVERY HAPPY SCRIBE CALL, ON THE RECORD

01 · USE CASES

What agents do in Happy Scribe.

Check a transcription's status

Poll a submitted transcription to see if it has finished before exporting the text.

Export a finished transcript

Export a completed transcription in the requested format for use in a video's captions.

Delete a transcription with confirmation

Delete an old transcription only after confirming with the uploader that it is no longer needed.

02 · ACTIONS

20 Happy Scribe actions, graded by risk.

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

read

Look things up. Allowed by default.

happy_scribe.get_rate_limit
Get API Rate Limit
happy_scribe.get_language_list
Get Supported Languages
happy_scribe.get_account_details
Get Account Details
happy_scribe.list_transcriptions
List Transcriptions
happy_scribe.get_signed_upload_url
Get Signed Upload URL
happy_scribe.retrieve_order
Retrieve Order

write

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

happy_scribe.create_subtitle
Create Subtitle
happy_scribe.create_translation_task
Create Translation Task
happy_scribe.hs_get_webhooks
Get Webhooks
happy_scribe.hs_confirm_order
Confirm Order
happy_scribe.hs_get_api_version
Get API Version
happy_scribe.hs_get_error_codes
Get Error Codes
happy_scribe.hs_retrieve_export
Retrieve Export
happy_scribe.hs_get_transcription
Get Transcription Details
happy_scribe.hs_export_transcription
Export Transcription
happy_scribe.hs_get_supported_formats
Get Supported Formats
happy_scribe.hs_create_translation_order
Create Translation Order
happy_scribe.hs_retrieve_translation_task
Retrieve Translation Task

destructive

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

happy_scribe.delete_webhook
Delete Webhook
happy_scribe.delete_transcription
Delete Transcription

03 · HOW IT WORKS

Happy Scribe in three steps.

01Your users connect Happy ScribeThey add their Happy Scribe api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “create Subtitle” can wait for the user, and “delete Webhook” can be denied outright.
03Any agent can actYour agent calls Happy Scribe 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('happy_scribe', {
  read: 'allow',
  write: 'ask',        // create_subtitle
  destructive: 'deny',  // delete_webhook
})

# 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 Happy Scribe connects.

Users add their Happy Scribe 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 Happy Scribe 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 Happy Scribe from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

Happy Scribe and Arc0, answered.

Q01

Can I use Happy Scribe with Claude, ChatGPT or Cursor?

Yes. Connect Happy Scribe 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 Happy Scribe actions you allow.

Q02

How do users connect Happy Scribe?

Users add their Happy Scribe 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 Happy Scribe actions can my agent take?

20 in total: 6 read, 12 write and 2 destructive, such as “create Subtitle”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Happy Scribe?

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 Happy Scribe too?

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

Get started

Plug Happy Scribe into your agent.

Your users connect Happy Scribe once, under your brand. Your agent gets 20 actions behind your policies, with every call on the record.

Connect Happy Scribe Browse all apps →

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