Skip to content

Connectors · AI

Rev.ai MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Rev.ai and the rest of your systems. It gives your agent 32 Rev.ai actions (20 reads, 6 writes and 6 that wait for a confirmation) and holds the Rev.ai credential itself, so the agent never does. It paces Rev.ai's limits and records every call.

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "rev_ai.jobs.list",  intent: "check which Rev.ai account is connected"}# List transcription jobs · read · 1 upstream call
  • 32actionsin one signed file
  • 20readlook, never change
  • 6writecreate and update
  • 6wait for a yesdestructive, confirmed first

Set up

Connect Rev.ai in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect Rev.ai.

    Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • access_tokenRev AI access token
    • regionYour Rev.ai region
    account { op: "connections.requirements", service: "rev_ai" }
    # free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "rev_ai.jobs.list" }# list transcription jobs · read · 1 upstream callcheck { action: "rev_ai.jobs.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Rev.ai at a glance

Sign-in
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
access_token
Setup fields
region
Limits we pace to
50 calls per 10 seconds, per connection
API covered
Rev AI (speech-to-text, custom vocabulary, alignment, language ID, sentiment and topic extraction) API Rev AI Asynchronous Speech-to-Text v1, Custom Vocabulary v1, Forced Alignment v1, Language Identification v1, Sentiment Analysis v1, Topic Extraction v1 (OpenAPI 3.0), at your region's rev.ai address, set when you connect
Built from
Rev.ai's documentation, read 23 October 2026docs.rev.aidocs.rev.aidocs.rev.ai
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
20 of 20 reads, for up to 5 minutes; a write clears what it affects
Shared entities
1, so ask can line Rev.ai up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Rev.ai.

32 actions in 14 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 20readlook, never change
  • 6writecreate and update
  • 6destructivewait for a confirmation
  1. Alignment jobs

    4

    2 read · 1 write · 1 destructive

    Submit a forced alignment job · List forced alignment jobs · Get a forced alignment job · Delete a forced alignment job

  2. Jobs

    4

    2 read · 1 write · 1 destructive

    Submit a transcription job · List transcription jobs · Get a transcription job · Delete a transcription job

  3. Language identification jobs

    4

    2 read · 1 write · 1 destructive

    Submit a language identification job · List language identification jobs · Get a language identification job · Delete a language identification job

  4. Sentiment analysis jobs

    4

    2 read · 1 write · 1 destructive

    Submit a sentiment analysis job · List sentiment analysis jobs · Get a sentiment analysis job · Delete a sentiment analysis job

  5. Topic extraction jobs

    4

    2 read · 1 write · 1 destructive

    Submit a topic extraction job · List topic extraction jobs · Get a topic extraction job · Delete a topic extraction job

  6. Vocabularies

    4

    2 read · 1 write · 1 destructive

    Submit a custom vocabulary · List custom vocabularies · Get a custom vocabulary · Delete a custom vocabulary

  7. Account

    1

    1 read · 0 write · 0 destructive

    Get account

  8. Alignment transcripts

    1

    1 read · 0 write · 0 destructive

    Get a forced alignment job's aligned transcript

6 more areas · 6 actions
  • Language identification results 1
  • Sentiment analysis results 1
  • Topic extraction results 1
  • Transcript summaries 1
  • Transcript translations 1
  • Transcripts 1

Top actions

The Rev.ai API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 1 of Rev.ai's 1 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
rev_ai.account.getGet accountGet account.readidentity.current_user.get307 connectors
rev_ai.jobs.listList transcription jobsList transcription jobs.readthis connector
rev_ai.jobs.createSubmit a transcription jobSubmit a transcription job.writethis connector
rev_ai.transcripts.getGet a job's transcriptGet a job's transcript.readthis connector
rev_ai.jobs.deleteDelete a transcription jobDelete a transcription job.destructivethis connector
rev_ai.vocabularies.listList custom vocabulariesList custom vocabularies.readthis connector
rev_ai.alignment_jobs.listList forced alignment jobsList forced alignment jobs.readthis connector
rev_ai.vocabularies.createSubmit a custom vocabularySubmit a custom vocabulary.writethis connector
rev_ai.alignment_jobs.createSubmit a forced alignment jobSubmit a forced alignment job.writethis connector
rev_ai.topic_extraction_jobs.listList topic extraction jobsList topic extraction jobs.readthis connector
rev_ai.topic_extraction_jobs.createSubmit a topic extraction jobSubmit a topic extraction job.writethis connector
rev_ai.sentiment_analysis_jobs.createSubmit a sentiment analysis jobSubmit a sentiment analysis job.writethis connector

Try it

Prompts to paste into Claude.

Each one names the Rev.ai actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    List transcription jobs in Rev.ai and tell me what stands out.

    callsrev_ai.jobs.list

  2. Writewrite

    Submit a transcription job in Rev.ai. Show me exactly what you will send before you save it.

    callsrev_ai.jobs.create

Governance for Rev.ai

Destructive actions wait for a yes.

6 Rev.ai actions are destructive. These are all of them:

  • Delete a transcription jobrev_ai.jobs.delete
  • Delete a custom vocabularyrev_ai.vocabularies.delete
  • Delete a forced alignment jobrev_ai.alignment_jobs.delete
  • Delete a topic extraction jobrev_ai.topic_extraction_jobs.delete
  • Delete a sentiment analysis jobrev_ai.sentiment_analysis_jobs.delete
  • Delete a language identification jobrev_ai.language_identification_jobs.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

dorev_ai.jobs.deleteconfirm_policy: human

Delete a transcription job?

intent: the user asked me to delete a transcription job

run suspended · waiting for a named person · key rev-ai-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "rev-ai-agent",  allowed_actions: ["rev_ai.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "rev_ai.jobs.delete", approver: "[email protected]" },    { match: "rev_ai.vocabularies.delete", approver: "[email protected]" },    { match: "rev_ai.alignment_jobs.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to Rev.ai only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Rev.ai costs on actionlake.

Every Rev.ai action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Rev.ai refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 32 Rev.ai actions
  • 32actions pageeach page of a long list is one call
  • 20reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Rev.ai action.

32 actions by area: the id your agent calls, what it does, and its effect.

Alignment jobs4
  • rev_ai.alignment_jobs.createSubmit a forced alignment jobwrite
  • rev_ai.alignment_jobs.deleteDelete a forced alignment jobdestructive
  • rev_ai.alignment_jobs.getGet a forced alignment jobread
  • rev_ai.alignment_jobs.listList forced alignment jobsread
Jobs4
  • rev_ai.jobs.createSubmit a transcription jobwrite
  • rev_ai.jobs.deleteDelete a transcription jobdestructive
  • rev_ai.jobs.getGet a transcription jobread
  • rev_ai.jobs.listList transcription jobsread
Language identification jobs4
  • rev_ai.language_identification_jobs.createSubmit a language identification jobwrite
  • rev_ai.language_identification_jobs.deleteDelete a language identification jobdestructive
  • rev_ai.language_identification_jobs.getGet a language identification jobread
  • rev_ai.language_identification_jobs.listList language identification jobsread
Sentiment analysis jobs4
  • rev_ai.sentiment_analysis_jobs.createSubmit a sentiment analysis jobwrite
  • rev_ai.sentiment_analysis_jobs.deleteDelete a sentiment analysis jobdestructive
  • rev_ai.sentiment_analysis_jobs.getGet a sentiment analysis jobread
  • rev_ai.sentiment_analysis_jobs.listList sentiment analysis jobsread
Topic extraction jobs4
  • rev_ai.topic_extraction_jobs.createSubmit a topic extraction jobwrite
  • rev_ai.topic_extraction_jobs.deleteDelete a topic extraction jobdestructive
  • rev_ai.topic_extraction_jobs.getGet a topic extraction jobread
  • rev_ai.topic_extraction_jobs.listList topic extraction jobsread
Vocabularies4
  • rev_ai.vocabularies.createSubmit a custom vocabularywrite
  • rev_ai.vocabularies.deleteDelete a custom vocabularydestructive
  • rev_ai.vocabularies.getGet a custom vocabularyread
  • rev_ai.vocabularies.listList custom vocabulariesread
Account1
  • rev_ai.account.getGet accountread
Alignment transcripts1
  • rev_ai.alignment_transcripts.getGet a forced alignment job's aligned transcriptread
Language identification results1
  • rev_ai.language_identification_results.getGet a language identification job's resultread
Sentiment analysis results1
  • rev_ai.sentiment_analysis_results.getGet a sentiment analysis job's resultread
Topic extraction results1
  • rev_ai.topic_extraction_results.getGet a topic extraction job's resultread
Transcript summaries1
  • rev_ai.transcript_summaries.getGet a job's transcript summaryread
Transcript translations1
  • rev_ai.transcript_translations.getGet a job's translated transcriptread
Transcripts1
  • rev_ai.transcripts.getGet a job's transcriptread

Questions

The Rev.ai MCP server, answered.

Is there a Rev.ai MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 32 Rev.ai actions across alignment jobs, jobs, language identification jobs and sentiment analysis jobs, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Rev.ai.

What do I need to connect Rev.ai?

Rev AI access token. Plus your region. The free call account { op: "connections.requirements", service: "rev_ai" } lists exactly what to paste.

Can an AI agent delete or change things in Rev.ai?

Only if its key allows it, and only with an explicit confirmation. 6 Rev.ai actions are destructive, including delete a transcription job, delete a custom vocabulary and delete a forced alignment job. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my Rev.ai API limit?

actionlake paces every call to the limits in the Rev.ai service file: 50 calls per 10 seconds per connection. Repeated reads are answered from cache (20 Rev.ai actions can be), which never reaches Rev.ai.

What does a Rev.ai action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (32 Rev.ai actions page). Cache hits, searches, dry runs and calls Rev.ai refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Rev.ai API does it cover?

The Rev AI (speech-to-text, custom vocabulary, alignment, language ID, sentiment and topic extraction) API Rev AI Asynchronous Speech-to-Text v1, Custom Vocabulary v1, Forced Alignment v1, Language Identification v1, Sentiment Analysis v1, Topic Extraction v1 (OpenAPI 3.0) at your region's rev.ai address, set when you connect. It is built from Rev.ai's documentation as read on 23 October 2026. 32 actions in 14 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Rev.ai data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Rev.ai credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent Rev.ai today.

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.