com.opennash.podcasts由 podcasts.opennash.com 發布官方發布者v1.2.0更新於 Nov 14, 2026
Search transcripts and sourced quotes from business and tech podcasts. Read-only, no key.
唯讀 MCP 伺服器，可用關鍵字檢索商業與科技播客的逐字稿、附出處的引述與主題頁，並依 id 取得全文。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/com.opennash.podcasts%2Fopennash-podcasts/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"opennash-podcasts": {
"type": "http",
"url": "https://podcasts.opennash.com/mcp"
}
}
}Search (ChatGPT-style)
Search facts, transcript passages and topics at once, for clients that only use the generic search/fetch pair (ChatGPT Deep Research). Returns up to 10 ids with a title, link and short snippet; pass an id to fetch for the full text. Other clients should prefer search_facts (quotes with speaker and timestamp) or search_transcripts (raw passages), which page and filter by show.
query必填Fetch (ChatGPT-style)
Get the full text for an id returned by search: an episode's summary and facts, a transcript passage with context, or a topic's facts.
id必填Search facts
Keyword search over sourced facts: each hit is a claim with the speaker's exact quote, timestamp, episode and links. Best for 'what did X say about Y' (search 'X Y', not the whole question). Results include show_slug and episode_slug for get_episode or get_transcript. Pages via offset/next_offset; total counts all matches; match says how strictly the keywords matched.
showlimitquery必填offsetSearch transcripts
Keyword search over full transcripts, returning matching paragraphs with a snippet, speaker, timestamp and a link to the exact paragraph. Use when search_facts finds nothing or you need the surrounding conversation: call get_transcript with show_slug, episode_slug and offset set to the hit's paragraph.
showlimitquery必填offsetList topics
List companies, people and subjects that have topic pages of sourced facts, most facts first. Filter with query; pass a slug to get_topic.
limitqueryoffsetGet topic
Get sourced facts about one company, person or subject across all shows, grouped by episode, 20 facts per page by default. total is the topic's fact count; pass next_offset as offset for the next page.
limittopic必填offsetList shows
List shows with their slug, host and episode count, 25 per page by title. Filter with query; descriptions are shortened.
limitqueryoffsetList episodes
List a show's episodes, newest first, with episode_slug, publish date and fact count. Pages via offset/next_offset.
show必填limitoffsetGet episode
Get an episode's summary, publish date, named speakers and every sourced fact with quote and timestamp.
show必填episode必填Get transcript
Get a transcript with speakers and timestamps, up to 40 paragraphs (about 12k characters) per page. total is the paragraph count; pass next_offset as offset for the next page.
show必填limitoffsetepisode必填已滿足適用檢查項的 83%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
請宣告包含 README 的 GitHub 儲存庫，或在 OAuth 受保護資源後設資料中提供 resource_documentation。
託管服務按其提供方的條款使用，因此這裡不要求授權條款。此檢查項不計入百分比。
il.co.ivreetmeet官方發布者
將助理連接到 IvreetMeet，用來搜尋與閱讀你的希伯來文會議逐字稿、摘要、決議與任務。
dev.nexteleven官方發布者
針對 Durable Agent Directory 的唯讀 MCP 伺服器，讓助理以關鍵字搜尋、檢視並比較代理基礎設施工具項目。
ai.whoscribe官方發布者
一個遠端 MCP 伺服器，讓助理搜尋並閱讀你自己的音訊與影片轉錄文字，包含講者與時間戳記。