ScribeToAny for developers

Server URL

https://scribetoany.com/api/mcp

Streamable HTTP transport, stateless JSON-RPC with JSON responses (no SSE stream, no session id). You don't need an API key: the client signs you in with OAuth the first time it connects.

Connect

claude mcp add --transport http scribetoany https://scribetoany.com/api/mcp

{
  "mcpServers": {
    "scribetoany": {
      "url": "https://scribetoany.com/api/mcp"
    }
  }
}

codex mcp add scribetoany --url https://scribetoany.com/api/mcp
codex mcp login scribetoany

gemini mcp add --transport http --scope user scribetoany https://scribetoany.com/api/mcp

{
  "servers": {
    "scribetoany": {
      "type": "http",
      "url": "https://scribetoany.com/api/mcp"
    }
  }
}

When the app opens ScribeToAny, sign in and select Allow access. To disconnect, remove ScribeToAny in the AI app's settings. To try the server without an AI app, run npx @modelcontextprotocol/inspector, choose Streamable HTTP and use the URL above.

Let your agent set it up

Using a coding agent (Claude Code, Codex, Gemini CLI, Cursor)? Paste this into it and it adds the server for you.

Set up ScribeToAny for me so I can transcribe audio and video and read my transcripts from here.

1. Add the remote MCP server https://scribetoany.com/api/mcp (Streamable HTTP, OAuth, no API key) under the name "scribetoany". Use your own command for it, e.g. `claude mcp add --transport http scribetoany https://scribetoany.com/api/mcp` in Claude Code, `codex mcp add scribetoany --url https://scribetoany.com/api/mcp` in Codex, or `gemini mcp add --transport http --scope user scribetoany https://scribetoany.com/api/mcp` in Gemini CLI.
2. Start the sign-in. It opens ScribeToAny in my browser, where I sign in and select Allow access.
3. Once it is connected, list my recent transcripts to confirm it works.

Transcribe files on your computer (CLI)

MCP clients other than ChatGPT can't pass a file from your computer. The ScribeToAny command-line tool can: it uploads the file to your account, waits for the transcript and saves it as text, SRT or VTT. Coding agents (Claude Code, Codex, Gemini CLI, Cursor) run it like any other command. It needs Node.js 20 or later.

npm i -g scribetoany
scribetoany auth login
scribetoany transcribe meeting.m4a --format srt --speakers

Add the agent skill so your agent knows the commands and options:

npx skills add scribetoany/skills --skill scribetoany

scribetoany auth login opens ScribeToAny in your browser, where you sign in and allow "ScribeToAny CLI", the same consent as for AI apps. Results go to stdout and progress to stderr; add --json for machine-readable output. Run scribetoany --help for every option.

Tools

Every result links back to the transcript in the ScribeToAny dashboard. The app can't edit or delete anything and never sees payment details.

Authentication

• OAuth 2.1 authorization code flow with PKCE (S256 only) and dynamic client registration, so clients register themselves. Access tokens last 1 hour; refresh tokens last 30 days.
• An unauthenticated request gets 401 with a WWW-Authenticate header pointing to the protected-resource metadata, which is how clients find the authorization server:

https://scribetoany.com/.well-known/oauth-protected-resource/api/mcp
https://scribetoany.com/.well-known/oauth-authorization-server

Access is granted only after you approve the client on the ScribeToAny consent screen, and only verified accounts can connect.

Limits

• Transcriptions started from an AI app count toward your plan like any other. The free plan includes 2 transcriptions a day and 100 minutes a month; paid plans raise both.
• get_transcript returns up to 120,000 characters; a longer transcript is cut off with a link to the full one.
• A JSON-RPC batch can hold up to 10 messages.
• YouTube, TikTok and Instagram links are not supported. Download the file and upload it on ScribeToAny instead.