Spoken MCP Server

MCP server for Spoken — fetch podcast transcripts as clean Markdown with real speaker names. Built for AI agents.

Local serverstdio

What is the Spoken MCP server?

If you already use Spoken, the spoken mcp server is the piece that lets your assistant work with it directly. MCP server for Spoken — fetch podcast transcripts as clean Markdown with real speaker names. Built for AI agents.

What the server does

Spoken is a transcript API that turns any published podcast into clean Markdown with real speaker names — not "Speaker 1." One API call returns named, timestamped text, ready for LLMs, RAG pipelines, summarizers, and search.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • LLM — friendly overview: https://spoken.md/llms.txt
  • search_podcasts — Find episodes by text or a pasted Spotify/YouTube URL
  • list_episodes — List a show's entire back-catalog from a podcast_id
  • get_transcript — Fetch an episode's transcript as Markdown with real speaker names
  • get_balance — Check remaining credits

Credentials and setup notes

Configuration is passed through the environment: SPOKEN_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Where it fits

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Spoken's toolset — LLM, search_podcasts, list_episodes and 2 more — is a fair guide to whether it matches your workflow. It is maintained by spokenmd; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
LLMfriendly overview: https://spoken.md/llms.txt
search_podcastsFind episodes by text or a pasted Spotify/YouTube URL
list_episodesList a show's entire back-catalog from a podcast_id
get_transcriptFetch an episode's transcript as Markdown with real speaker names
get_balanceCheck remaining credits

How to install the Spoken MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
SPOKEN_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Spoken to LLM.
  • Use Spoken to search podcasts.
  • Use Spoken to list episodes.

Frequently asked questions

It connects Spoken to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (LLM, search_podcasts, list_episodes, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Spoken directly.