# podcast-commerce-mcp [Health: Active]

**Category:** 🎙️ Podcasts  
**Repository:** https://github.com/teamsincetoday/podcast-commerce-mcp  
**GitHub Stars:** 0  
**npm Downloads (last month):** 168  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/podcast-commerce-mcp

## Description
Extract product mentions from podcast transcripts with affiliate signals. Free tier 200/day.

## Tools
Capabilities this server exposes over MCP:

- **extract_podcast_products** — Extract affiliate products, sponsored brands, and host recommendations from a podcast transcript (text input only — does not process audio or video). Returns product name, category, confidence score, recommendation strength, and sponsor flag. Call this before analyze_episode_sponsors or track_product_trends — both tools reuse its cache. Use for podcast monetization, affiliate program discovery, and episode-to-episode trend tracking. Returns empty products array (not an error) when no product mentions are found. Example: episode_id='huberman-ep-301', category_filter=['physical_goods','supplement'].
- **analyze_episode_sponsors** — Identify and score podcast sponsor segments (host-read ads, mid-roll, pre-roll). Returns sponsor name, ad placement type, call-to-action URL, estimated read-through rate, and revenue metrics based on category benchmarks — not live ad-platform data. Use for advertising intelligence, CPM estimation, and sponsor outreach research. Use this tool when you need sponsor metrics only; for the full product and recommendation list use extract_podcast_products instead. Reuses cached extraction when episode_id matches a prior extract_podcast_products call. Example: episode_id='huberman-ep-301' → returns [{sponsor:'Athletic Greens', placement:'pre-roll', estimated_cpm:25, read_through_rate:0.72}].
- **track_product_trends** — Compare affiliate product and brand mention frequency across multiple podcast episodes to detect rising, stable, and declining trends. Returns trend velocity, mention count per episode, and category breakdown. No AI call — computed from cached extraction data only. Use for affiliate marketing optimization, seasonal product tracking, and content calendar planning. Requires prior extract_podcast_products call for each episode_id — returns an error listing missing IDs if any are not in cache. Example: episode_ids=['ep-301','ep-302','ep-303'].
- **compare_products_across_shows** — Compare and rank product mentions across multiple podcast shows using cached extractions — no re-run or extra AI cost. Collapses a 3-call manual join into 1 tool call with entity resolution to match the same product across different show mentions. Returns ranked products with per-show context, average confidence, recommendation consensus, and brand aggregation. Use for multi-show affiliate research, 'best of' page generation, and cross-show brand ranking. Requires prior extract_podcast_products call for each show_id — returns error listing missing IDs if any are absent. Example: show_ids=['epic-gardening','garden-answer'], min_confidence=0.85.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "podcast-commerce-mcp": {
    "command": "npx",
    "args": ["-y","podcast-commerce-mcp"],
    "env": {
      "OPENAI_API_KEY": ""
    }
  }
}
```

**Requires environment variables:** `OPENAI_API_KEY` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What podcast-commerce-mcp MCP server does

The podcast-commerce-mcp MCP server turns podcast transcript text into structured commerce data for AI agents. Its extraction workflow identifies mentioned products and brands, records surrounding context and speaker information, and assigns confidence and recommendation-strength values. Results may also include sponsor segments and affiliate-related fields.

The server supports both individual episode analysis and comparisons across a catalog of previously processed episodes. It can identify sponsor reads, estimate how much of a sponsor segment was delivered, follow product mention patterns over time, and rank products across multiple shows after resolving entities that refer to the same brand.

## How it works

A client sends a transcript, or a URL to a text file, to the extraction tool. Optional inputs include an episode identifier for caching and category filters such as SaaS or physical goods. The returned data includes products, mention counts, context, speakers, confidence values, recommendation strength, sponsor information, and processing metadata.

Trend analysis uses episode identifiers that have already been extracted and cached. It reports whether product mentions are rising, stable, or falling, along with average recommendation strength and the leading category. Cross-show analysis accepts show identifiers and can filter by minimum show count or confidence. Its results include show coverage, average confidence, and whether recommendations are unanimous, majority-based, mixed, or rare.

## Setup and configuration

The podcast-commerce-mcp MCP server can be installed from npm with `npm install podcast-commerce-mcp` and started locally with `npx podcast-commerce-mcp`. Local execution requires `OPENAI_API_KEY`. Optional settings identify an agent, configure paid API keys, select the SQLite cache location, and enable payment enforcement.

Agents can also use the hosted streamable MCP endpoint at `https://podcast-commerce-mcp.sincetoday.workers.dev/mcp`. The documented remote configuration does not require an API key and provides a free allowance of 200 calls per day per agent. Paid usage is listed as $0.01 per call and uses configured MCP API keys.

## Tools and capabilities

- `extract_podcast_products` finds products and brands in a transcript and returns confidence, context, speaker, recommendation, and related metadata.
- `analyze_episode_sponsors` identifies sponsor segments and estimates read-through rates.
- `track_product_trends` compares products across cached episodes.
- `compare_products_across_shows` ranks products mentioned by multiple shows with entity resolution.
- `generate_show_notes_section` converts previously extracted product data into a formatted, shoppable show notes block. Markdown and a full style are documented options.

## Limitations and notes

Trend tracking and show notes generation depend on data that was previously extracted and cached. The local package depends on an OpenAI API key, while the hosted endpoint has its own daily free-use limit.

Extraction quality and confidence values describe the server's analysis; they should be reviewed before publishing affiliate links, sponsor claims, or commercial recommendations. The repository lists MIT licensing and provides development commands for type checking, tests, and builds.

_Full upstream README: https://allmcps.com/mcp/podcast-commerce-mcp/readme_