HPR Knowledge Base MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Server port (default: 3000) | 3000 |
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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_episodesA | Search HPR episodes by keywords in title, summary, tags, or host notes. Can filter by host, series, tags, and date range. |
| get_episodeA | Get detailed information about a specific HPR episode including transcript if available |
| search_transcriptsA | Search through episode transcripts using phrases or multiple terms with AND/OR matching and optional host filters |
| get_host_infoA | Get information about an HPR host including all their episodes |
| get_series_infoB | Get information about an HPR series including all episodes in the series |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| HPR Statistics | Overall statistics about the HPR knowledge base |
| Recent Episodes | List of 50 most recent HPR episodes |
| All Hosts | List of all HPR hosts |
| All Series | List of all HPR series |
TDQS
Scored across 5 tools
Each tool targets a distinct aspect: episode details, host info, series info, episode search, and transcript search. No functional overlap.
All tools follow a consistent verb_noun pattern in snake_case (get_*, search_*), making them predictable.
5 tools are well-scoped for a knowledge base server, covering retrieval and search without unnecessary bloat.
The set covers the core data model (episodes, hosts, series, transcripts) with both individual lookups and search, leaving no obvious gaps for a read-only knowledge base.