Verbatim Transcribe MCP Server

Audio → transcript → insight. A local, self-hosted web app that turns hours of audio/video into timestamped text - and then into structured, cross-referenced opinion research.

People connecting media tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-22 · ★ 4 · #90 OF 155 MAINTAINED MEDIA · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Verbatim Transcribe

before you install - you'll need

Set GEMINI_API_KEY, DASHSCOPE_API_KEY before connecting.

Claude Code

claude mcp add xyzxinlu-max-getaudio -- uvx verbatim-transcribe-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "xyzxinlu-max-getaudio": {
      "command": "uvx",
      "args": [
        "verbatim-transcribe-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package verbatim-transcribe-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.xyzxinlu-max is GitHub-verified and matches the repo owner

03 · What Verbatim Transcribe can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v1.0.0 · 2026-08-22

Verbatim v1.0.0 - first packaged desktop release · Local, self-hosted audio/video transcription + AI creator-analysis platform. This is the first release with installable desktop apps for macOS and Windows. · Downloads…

04 · Who maintains Verbatim Transcribe

Verbatim Transcribe is maintained by xyzxinlu-max. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

repository: github.com/xyzxinlu-max/getaudio
category: media - ranked #90 of 155 actively-maintained media servers as of 2026-08-25.
release cadence: 1 release in the last 90 days (latest 2026-08-22)
registry: io.github.xyzxinlu-max/verbatim-transcribe-mcp (active, first published 2026-08-20)
packages: pypi:verbatim-transcribe-mcp

06 · Verbatim Transcribe FAQ

What is Verbatim Transcribe?

Audio → transcript → insight. A local, self-hosted web app that turns hours of audio/video into timestamped text - and then into structured, cross-referenced opinion research.

Is Verbatim Transcribe still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-22 and it shipped 1 release in the last 90 days. We re-verify nightly.

How do I install Verbatim Transcribe?

Run `uvx verbatim-transcribe-mcp`. The README documents 2 environment variables (GEMINI_API_KEY, DASHSCOPE_API_KEY) to set first. Set GEMINI_API_KEY, DASHSCOPE_API_KEY before connecting. You can also paste the ready-made client config above.

Does Verbatim Transcribe run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Verbatim Transcribe

Alternatives to Verbatim Transcribe

Maintained media servers if Verbatim Transcribe isn't the fit.

More media MCP servers · Bilibili MCP Server · Video Extract · 💯 YouTube Transcript + YouTube Search MCP for AI Agents · Nanobanana MCP Server · YouTube Summarize

More Python MCP servers · Agent Memory Os · Open Computer Use · Yantrikdb MCP · Learning Model Context Protocol · see all