Rev.ai MCP server

Transcribe audio with Rev.ai: submit jobs by URL, read transcripts, summaries and captions. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.

Claude claude.ai · Desktop

  1. Open Customize → Connectors, then click + Add → Add custom connector.
  2. Enter the name Rev.ai and this URL, then click Add:
    https://rev-ai.usefulapi.io/mcp
  3. Claude opens the login page: enter your Rev.ai access token.
  4. In a chat, click + → Connectors and turn on Rev.ai.

Team and Enterprise: an Owner adds the connector for the organization first.

Claude Code

Run this command, then run /mcp in Claude Code to log in:

claude mcp add --transport http rev-ai https://rev-ai.usefulapi.io/mcp

Cursor

Add to Cursor or add this to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "rev-ai": {
      "url": "https://rev-ai.usefulapi.io/mcp"
    }
  }
}

VS Code

Add to VS Code or add this to .vscode/mcp.json:

{
  "servers": {
    "rev-ai": {
      "type": "http",
      "url": "https://rev-ai.usefulapi.io/mcp"
    }
  }
}

Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.

live12 toolsFree 100 tool calls / monthPro $9/mo · $90/yr

Before you connect

The login page asks for your Rev.ai access token.

Create one at rev.ai → Access Token → Generate New Access Token (an account can hold 2 tokens). Rev.ai shows a token only once, so copy it right away. Your token is used only to call the Rev.ai API on your behalf; it is never shown to anyone.

Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Rev.ai access token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.

Tools 12

ToolTypeWhat it does
revai_get_accountread
Get account and balance
The Rev.ai account behind the token: email, free, purchased, total and invoiced balance (USD) and whether HIPAA is on. GET /account.
revai_list_jobsread
List transcription jobs
List transcription jobs from the last 30 days, newest first: id, status (in_progress, transcribed, failed), name, duration, language, failure reason. Page with starting_after = the previous reply's next_starting_after. GET /jobs.
revai_get_jobread
Get job status
One transcription job by id: status (in_progress, transcribed, failed), timestamps, duration, language, failure reason. Poll this until status is transcribed. GET /jobs/{id}.
revai_submit_jobwrite
Submit transcription job
WRITE: start an asynchronous machine transcription job for an audio or video file at a public URL. It uses Rev.ai credit (free credit first). Returns the job with status in_progress; then poll revai_get_job and read the result with revai_get_transcript. Human transcription is not offered. POST /jobs.
revai_delete_jobwrite
Delete job
WRITE: permanently delete a finished (transcribed or failed) job with its media and transcript. This cannot be undone. A job still in progress cannot be deleted. DELETE /jobs/{id}.
revai_get_transcriptread
Get transcript
The transcript of a transcribed job. format=text (default) is plain text with speaker labels and timestamps; format=segments is a list of {speaker, start, end, text} per speaker turn (seconds). Long transcripts are paged: repeat with next_offset until it is null. GET /jobs/{id}/transcript.
revai_get_summaryread
Get transcript summary
The summary of a transcribed job. It exists only if the job was submitted with summarization_type. Paged by character like revai_get_transcript. GET /jobs/{id}/transcript/summary.
revai_get_captionsread
Get captions
Captions for a transcribed job as SRT (default) or WebVTT. Long files are paged by character: repeat with next_offset until it is null. For multichannel jobs pass speaker_channel. GET /jobs/{id}/captions.
revai_usage_statusmeta
Usage status (free-tier meter)
Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter.
revai_request_featuremeta
Request a missing feature
Tell usefulapi that the user needs something the Rev.ai tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter.
revai_upgrademeta
Upgrade to Pro (unlimited)
Subscribe to the Pro plan for UNLIMITED Rev.ai tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter.
revai_cancel_subscriptionmeta
Cancel the Pro subscription
Cancel the caller's Rev.ai Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run revai_upgrade later to undo the cancel before the period ends. Does not count against the meter.

Pricing

PlanPriceLimit
Free$0100 tool calls / month
Proper user$9/mo · $90/yrUnlimited

Pro covers this Rev.ai server only. Subscribe with revai_upgrade (it returns a Stripe Checkout link). Cancel any time with revai_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running revai_upgrade before then undoes the cancel. Or write to [email protected].

FAQ

Is this an official Rev.ai product?

No. usefulapi is an independent service. It is not affiliated with or endorsed by Rev.ai. The server calls the Rev.ai API with your own Rev.ai access, so it sees only the data that your account can see.

What do I need to connect?

The login page asks for your Rev.ai access token. See Before you connect for where to find it.

Do I put my Rev.ai key or an Authorization header in the client config?

No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Rev.ai access token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.

How do you keep my Rev.ai credentials?

The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Rev.ai API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Rev.ai.

Can the AI change my Rev.ai data?

Yes, if you approve it. 2 of the 8 Rev.ai tools can create or change data. The other 6 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.

What does it cost?

The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this Rev.ai server only. Run revai_usage_status to see how many calls you used.

How do I subscribe or cancel?

Ask the AI to run revai_upgrade: it returns a Stripe Checkout link. To cancel, run revai_cancel_subscription. Pro continues to the end of the paid period.

What if a Rev.ai tool that I need is missing?

Tell the AI what you wanted to do. It can send the request with revai_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.

Which AI clients can I use?

Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, Cursor, VS Code, Windsurf and others.

This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.

More AI MCP servers

BannerbearDeepInfrafal.aiFireworks AILambda LabsMindeeMistralNomic AtlasPortkeySpeechmaticsTogether AI

All AI servers →