# Podcast Transcripts On-Demand

Podcast Transcripts On-Demand — an MCP server for real-time access to podcast transcripts. Search episodes by keyword, topic, or show name; retrieve full transcripts directly in your IDE.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 2007 installs
- Author: petabloom
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/petabloom/podcasts
- Updated: 2026-03-19
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/podcast-transcripts-on-demand

## What it does

The server indexes podcasts and offers multiple search methods. Keyword search matches episode and show names exactly, while topic search grasps intent—a query about AI safety finds episodes on alignment, AGI risks, or frontier model evaluation without requiring the exact phrase. You can also pull the most recent episodes across the entire catalog.

Each episode has a show GUID and episode GUID, passed to the transcript tool. Text arrives in chunks; navigate between them using `next_cursor`. The server runs on Claude Code, Codex, Cursor, GitHub Copilot, Windsurf, Cline, Zed, and Gemini CLI.

Transcripts refresh in real time as episodes drop. Built-in feedback channel lets you report bugs, request features, or flag missing data.

## Requirements
- Remote server: `https://podcasts--petabloom.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http podcasts https://podcasts--petabloom.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add podcast-transcripts-on-demand --url https://podcasts--petabloom.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "podcast-transcripts-on-demand": {
            "url": "https://podcasts--petabloom.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "podcast-transcripts-on-demand": {
            "type": "http",
            "url": "https://podcasts--petabloom.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http podcast-transcripts-on-demand https://podcasts--petabloom.run.tools
```

## When to use it
- search for a podcast by title or keywords
- retrieve the transcript of a specific episode
- find episodes by topic meaning, not exact phrase match
- see the latest published episodes
- submit a bug report or feature request

## Example prompts
- Find podcasts about machine learning and show me the latest episodes
- Get the full transcript for an episode using its show and episode GUIDs
- Search episodes on AI safety and next-generation model evaluation

## Similar
- [Vidskim: YouTube transcripts](https://affpapa.org/en/nevibecode/mcp/vidskim-youtube-transcripts.md) — MCP server
- [podcast-generation](https://affpapa.org/en/nevibecode/skills/bytedance-podcast-generation.md) — skill · 2400 installs
- [podcast-content-analyzer](https://affpapa.org/en/nevibecode/agents/podcast-content-analyzer.md) — subagent · 474 installs
- [podcast-edit](https://affpapa.org/en/nevibecode/skills/podcast-edit.md) — skill · 291 installs
- [ai-podcast](https://affpapa.org/en/nevibecode/skills/ai-podcast.md) — skill · 238 installs
- [podcast-production](https://affpapa.org/en/nevibecode/skills/podcast-production.md) — skill · 133 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
