@pipeworx/pod-researcher

Connect: https://pipeworx.io/mcp — every tool in the catalog, including @pipeworx/pod-researcher’s. Install: one-click buttons

No MCP client? Skip the connection: POST https://gateway.pipeworx.io/v1/tools/search_packs {"query":"..."} to find a tool below, GET /v1/tools/<name> for its schema, POST the same URL with arguments for the data — see For AI agents.

Tools: 8

Podcast prospecting for guest booking and sponsorship: given a topic and a purpose, returns active podcasts whose recent episodes cover the topic, each with the best contact route the show itself published, the episodes that prove the fit, and your own outreach history so you never pitch the same show twice.

Tools

• find_podcast_contacts(topic, purpose, require_route?, language?, country?, active_only?, include_engaged?, limit?, cursor?) — active shows ranked by topical fit, each with best_route (or route_status: "none_found" plus what was checked), evidence episodes, coverage counts and data_as_of. purpose is guest or sponsor; routes designated for that purpose rank first, and a general contact or a person’s published address is a labelled fallback. require_route: true returns only shows that have one.
• get_podcast_profile(id) — one show in full: identity, activity status, feed health, latest episodes, every published route. id is a show_id, an RSS feed URL (moved feeds resolve by their old URL) or a podcast:guid.
• refresh_podcast(id) — re-read one show’s RSS feed now rather than waiting for its next scheduled check.
• watch_podcast_topic(topic, purpose, ...) / get_podcast_topic_changes(watch_id?) — save a search and get the shows that newly match it.
• record_podcast_outreach(show_id, outcome, scope?, contact_id?) — record contacted / replied / declined / booked / bounced / do_not_contact / clear. Declined and do_not_contact shows leave your searches; a scope: "person" record hides every show that publishes that person’s address. Private to your account.
• list_podcast_transcripts(id, episode?, limit?) — which episodes have a publisher-provided transcript and where: reads the show’s RSS feed live and lists every episode’s Podcasting 2.0 <podcast:transcript> links (URL, declared type, format srt / vtt / json / text / html, language, rel). Episodes without one stay in the list as transcript_status: "no_publisher_transcript"; a show with none says so in note with transcript_coverage: "none" and the episode list intact. id is a show_id, podcast:guid or feed URL (a feed URL the index does not know is read directly).
• search_podcast_transcript(id, query, episode?, format?, limit?, window_seconds?) — passages of one episode’s transcript that match a query, each with start / end (hh:mm:ss and seconds), the speakers when the file names them, and matched_terms. Defaults to the newest episode with a transcript; episode takes a guid, URL, episode number or title words. Formats parsed: SRT, WebVTT, Podcasting 2.0 JSON, plain text (timestamped lines, or untimed text returned with timing_note) and HTML. found: false, reason: "no_publisher_transcript" names the episodes that do have one. A feed or file that fails to fetch or parse throws an error naming the upstream HTTP status or the format.

Auth

Keyless to search. watch_podcast_topic, get_podcast_topic_changes and record_podcast_outreach need a signed-in account (an API key from pipeworx.io/signup): outreach history is kept per account, and an anonymous caller has none. This pack runs only on the Pipeworx gateway; a standalone build refuses every call rather than returning an empty list.

Contacts: what is returned and how it is labelled

Every address a show publishes in its own RSS feed or on its own website is returned, labelled:

• holder_type: role (a function inbox such as booking@ or sponsorships@), hosting_account_owner (the itunes:owner address from the feed, usually the host), or person (an individual’s own address).
• purpose (guest, sponsor, general) and confidence (designated when the show invited that purpose in words, fallback otherwise), plus match on the best route: designated_for_purpose or general_fallback.
• source_url (the page or feed it was read from) and last_observed.

Addresses are never synthesised. A global removal list is honoured at serve time. record_podcast_outreach never takes an address: a call carrying anything email-shaped is refused without repeating it, and a person-level record stores a SHA-256 of the address, not the address.

Data sources

• Podcast Index open directory (https://podcastindex.org) — which podcasts exist, their feed URLs and identifiers.
• Each show’s RSS feed — episodes, publishing cadence, the itunes:owner address and invitation lines in episode notes.
• Each show’s own website — its guest, advertise and contact pages.
• Each show’s own RSS feed and the transcript file its <podcast:transcript> tag links to (Podcasting 2.0 namespace, https://podcastindex.org/namespace/1.0) — fetched live per call, never stored; every transcript response carries the feed URL, the file URL and the time each was fetched in data_as_of. Transcripts are the publisher’s: whether one exists, its accuracy and its timing are theirs.

Matching is on words in episode titles and show notes (the latest ~30 episodes per show), so a show that never names the topic in its notes is not found. Generated-content spam is left out by a classifier that also catches some real shows whose episode notes disclose AI assistance. Contact coverage is still growing: route_check on each result says whether the show’s website has been read yet, so “none found” and “not looked at yet” are distinguishable.

Tools

• find_podcast_contacts — Find ACTIVE podcasts whose recent episodes cover a topic, each with the best published contact route for booking a guest or buying sponsorship. Searches episode titles and show notes across ~740k podc
• get_podcast_profile — One podcast in full: identity (title, feed URL, website, podcast:guid, Apple id), activity status and feed health, the latest episodes, and EVERY published contact route with holder_type (person / rol
• refresh_podcast — Ask for one podcast’s RSS feed to be read again now rather than at its next scheduled check. Returns the show’s current state and when the refresh was queued; new episodes show up in get_podcast_profi
• watch_podcast_topic — Signed-in accounts: save a topic x purpose search so get_podcast_topic_changes can report podcasts that newly match it. Records the current matches as the baseline, so get_podcast_topic_changes return
• get_podcast_topic_changes — Signed-in accounts: for your topic watches (or one, by watch_id), the podcasts that match now and did not at the last check, with their best contact route. Each call moves the baseline forward, so a s
• record_podcast_outreach — Signed-in accounts: record what happened when you reached out to a podcast, so find_podcast_contacts stops suggesting it. outcome: contacted, replied, declined, booked, bounced, do_not_contact or clea
• list_podcast_transcripts — Which episodes of a podcast have a publisher-provided transcript, and where: reads the show’s own RSS feed live and lists every episode’s Podcasting 2.0 podcast:transcript links with their format (S
• search_podcast_transcript — What a podcast episode actually said about a topic, with timestamps: fetches the episode’s publisher-provided transcript (Podcasting 2.0 podcast:transcript, as SRT, WebVTT, JSON, plain text or HTML)