Spoken MCP Server

by spokenmd Your server? Claim it

local only

Spoken runs on your own machine — the client starts it, so there is no endpoint to ping. 64 installs a week from npm. Last commit 27 Aug 2026.

Podcast transcripts as clean Markdown with real speaker names — via the Spoken API.

Installs per day peak 50 · avg 15 · -34% w/w

a month agotoday

Installs / week

npm · spoken-mcp

Stars

0 open issues

27 Aug 2026

Last commit

0 releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Spoken every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add spoken -- npx -y spoken-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "spoken": {
      "args": [
        "-y",
        "spoken-mcp"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.spoken]
command = "npx"
args = ["-y", "spoken-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "spoken": {
      "args": [
        "-y",
        "spoken-mcp"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "spoken": {
      "args": [
        "-y",
        "spoken-mcp"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: SPOKEN_API_KEY (API key from spoken.md (starts with pt_). Defaults to pt_demo (search works fully; transcripts limited to the demo episode).). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Spoken

same job, measured the same way

Fetch Extract

by cedrickouma

MCP server (stdio): fetch web pages as clean readable markdown via the AgentForge API

26 installs/wk answering

Whispernotes

by mazzzystar

Search, read, and create speech-to-text transcripts on-device with the Whisper Notes Mac app.

local only

Promptready MCP

by hydrojwh

Convert PDF/CSV to Markdown with AI-powered OCR via the PromptReady cloud API.

983 installs/wk local only

Particle Pro

by particle

Podcast intelligence for agents: transcripts, clips, speaker diarization, mention tracking.

28 tools answering

Packforai MCP

by zymsj8j9z9-ship-it

Convert PDF, DOCX, XLSX, CSV, JSON into clean, AI-ready Markdown via the PackForAI API.

31 installs/wk local only

Phone Bud

by phone-bud

AI voice agents that make real phone calls: single calls or campaigns, with transcripts and notes.

answering

Presentr Analyze

by michaelw-pr

Podcast and media analysis: transcripts, captions, chapters, ad markers and show notes.

answering

Extract

by averra

URL-to-Markdown API for AI pipelines — clean markdown with metadata and caching.

60 installs/wk local only

Spoken — questions

Answers built from our own checks of this server.

Why is there no uptime for Spoken?

Spoken runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package spoken-mcp was installed 64 times last week.

How do I connect Spoken?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls spoken-mcp straight from npm; nothing to host, nothing to sign up for.

How many people use Spoken?

The npm package spoken-mcp was installed 64 times in the last week. Week over week that is -34%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Spoken open source?

Yes — it is published under the MIT licence, written in TypeScript and 4 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.