Entra News Podcast
by darrenjrobinsoncommunityv0.1.2
1
An MCP server that searches transcripts of the Entra.Chat Microsoft Entra podcast on YouTube and returns timestamped links to relevant moments. It also exposes episode, guest, and community tool lookup over a locally cached transcript database refreshed weekly.
From the registry: Search Entra.Chat podcast transcripts — Merill Fernando's Microsoft Entra podcast on YouTube
Install & configure
Prerequisites
- optionalInstall Node.js 22+Node.js version 22 or later is required because the server uses the built-in node:sqlite module.https://nodejs.org/'}],
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `entra-news-podcast` MCP server into my current AI client (that's you).
Optional prerequisites:
- Install Node.js 22+ — Node.js version 22 or later is required because the server uses the built-in node:sqlite module. (https://nodejs.org/'}],)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","entra-news-podcast-mcp"]
- optional environment variables:
- `OPENAI_API_KEY`: Optional OpenAI API key to enable semantic/hybrid search. Without it, the server still works using BM25 keyword search only. (example: `<your-openai-api-key>`)
- `ENTRA_PODCAST_DB_PATH`: Optional path to a local SQLite database file to override the default auto-downloaded cached database. (example: `<your-local-database-path>`)
Note: On first run, the server automatically downloads the transcript SQLite database from the project's GitHub Releases and caches it locally. No per-user infrastructure is required.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: On first run, the server automatically downloads the transcript SQLite database from the project's GitHub Releases and caches it locally. No per-user infrastructure is required.
Tools (6)
search_entra_podcasts
Search episode transcripts using hybrid, semantic, or keyword modes and return episode details with timestamped YouTube links.
get_episode
Get a full episode by video ID, episode number, or date, including metadata, guests, chapters, and transcript.
list_episodes
Browse episodes with optional filters by year, month, and guest name.
list_guests
List all podcast guests with profile links, appearance counts, and latest appearance.
get_guest
Get one guest’s profile links and every episode they appeared on.
find_tool_mentions
Find community tools discussed on the show with timestamped links.
Environment variables
OPENAI_API_KEYEnables semantic/hybrid search by generating embeddings; without it, keyword search is used.ENTRA_PODCAST_DB_PATHOverrides the database path to use a local database file instead of the downloaded cache.YTDLP_PROXYRoutes yt-dlp traffic through a proxy during database refresh/ingest runs.Packages
entra-news-podcast-mcp
npmv0.1.2transport: stdio
Details
- Language
- TypeScript
- License
- MIT
- Released
- Jul 16, 2026
- Last commit
- Aug 5, 2026
- Registry name
- io.github.darrenjrobinson/entra-news-podcast