Every library is an API.
Read, search, and cite any podcast hosted on PodHood — over REST, MCP, or plain Markdown. All read access to published content is anonymous: no API key, no sign-up.
One index, three protocols
The same structured Brief that powers each library's pages is exposed as a REST API for programs, an MCP server for AI agents, and Markdown for anything that reads text.
MCP — for AI agents
Every channel exposes an anonymous, read-only MCP server over Streamable HTTP. It provides one tool, search: ask a natural-language question, get back ranked episodes and grounded, timestamped quotes — each with a citation URL to the exact second.
https://<channel>.podhood.com/mcpOptional parameters: topK, maxSegmentsPerEpisode, includeText, fast, episodeIds. Each library’s Ask dialog ships install recipes for 30+ MCP clients — Claude, ChatGPT, Cursor, VS Code, and more.
REST — search a channel
The versioned surface is /api/v1; every documented endpoint is a read-only GET — idempotent and safe to retry — and a breaking change would ship as /api/v2with Deprecation and Sunset headers on the old version. Hybrid (semantic + keyword) search over a channel’s published episodes. Facet filters accept comma-separated ids: topicIds, personIds, entityIds, episodeIds — plus collectionId and year. Pass fast=true for keyword-only search.
curl "https://podhood.com/api/v1/channels/{slug}/search?query=pricing%20strategy"REST — browse episodes
A keyset-paginated list of published episodes with the same facet filters plus sort. Pass the response’s nextCursor back as cursor for the next page.
curl "https://podhood.com/api/v1/channels/{slug}/episodes"REST — episode resources
Published episodes are anonymously readable; unpublished ones 404. Errors are JSON with an error message — never HTML.
GET /api/v1/episodes/{episodeId}/transcript # word-level transcript
GET /api/v1/episodes/{episodeId}/chapters # chapters with key moments
GET /api/v1/episodes/{episodeId}/related # topically related episodesMachine-readable surfaces
- OpenAPI spec — the full REST surface with typed parameters and operation ids.
- auth.md — how agents authenticate (short version: they don’t need to; read access is anonymous).
- llms.txt — the platform index; every channel host serves its own, listing its episodes and MCP endpoint.
- Markdown twins — append
.mdto any episode or marketing page URL (/index.md, /pricing.md, this page at /developers.md). sitemap.xmlandrobots.txton every host — AI crawlers are welcome, and episode pages carry Schema.org JSON-LD (PodcastEpisode, deep-linked Clip nodes for chapters and key moments, speakers, entities).
The structure that makes a podcast citable is the same structure that makes it programmable.
