podcast-recommendations
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rouletteB | Discover long-tail podcasts by topic — randomized probes surface shows the charts recycle forever |
| trendingA | Apple's top podcasts overall or by genre, enriched with feed URLs and episode counts |
| peekA | Fetch any podcast's RSS feed and return the show's cadence, typical episode length, and latest episodes |
| list_genresA | The genre names accepted by roulette/trending |
| skills_listA | List available skills (guidance playbooks) for using this server well — read one with skill_read |
| skill_readA | Fetch the full content of one skill by name (from skills_list) — guidance on error recovery and effective use |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| surprise-me | Fully random discovery spin — no topic, long tail only. |
| commute-pick | Discover a show that fits a commute budget (cadence + episode length matched to minutes available). |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| discovery-vs-lookup | When to use roulette vs trending vs peek, and how to present a pick. |
| interpreting-errors | How to read this server's error shapes (empty pool, feed failures, genre misses) and recover. |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: roulette for random long-tail discovery, trending for top charts, peek for inspecting a specific feed, list_genres as a helper for the first two, and skills tools for meta-guidance. No two tools overlap in function, so an agent can reliably pick the right one.
Naming conventions are inconsistent. list_genres follows verb_noun, but skills_list and skill_read invert to noun_verb, while roulette, trending, and peek are single nouns or verbs without a pattern. This mixed style makes it harder to predict tool names.
Six tools is well-scoped for a podcast recommendation server: four core data-access tools plus two meta-tools for guidance. Each earns its place, and the count is neither sparse nor overwhelming.
The tool surface covers the primary workflows: discovering podcasts (roulette, trending), inspecting them (peek), and enumerating valid genres (list_genres). A minor gap is the lack of a direct search by podcast name (peek requires a feed URL), but this is not a fundamental hole for the server's purpose.