Ourword

io.github.woowoethPublished by GitHub account woowoethv1.0.0Updated Oct 24, 2026

Search Chinese deep-reads of 190+ podcasts; every point and quote has an audio timestamp.

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Searches Chinese-language deep-read summaries of 190+ podcasts, returning key points, quotes and figures with audio timestamps.

What you can do
  • Search episodes by keyword, show or category
  • Fetch one episode's key points, quotes, figures and terms, each with a timestamp
  • List shows with how many deep-reads each has and the date of the latest
  • List recent deep-reads, optionally filtered by category
When to use it
Useful when an assistant needs to find which podcast said what on a topic, or pull a citable, timestamped summary of a specific episode without loading a multi-megabyte text file into context.
Requirements
Runs locally as a Python 3.10+ script using only the standard library; no third-party dependencies. Data is fetched live from the public site, so network access is needed. The optional OURWORD_SITE environment variable overrides the site root.
Before you install
No verbatim transcripts are provided, only the site's own summaries, figures and short attributed quotes. Queries and lookups are sent to the remote site. Setting OURWORD_SITE points the server at a different site root.

Installation

In SourceWeft

  1. Open Ourword in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

ourword MCP server

把 原声（ourword.ai）的播客深读开放给 agent 查。

每天从 190 多档中英文播客里挑出值得记住的判断，写成中文深读。要点、金句、数字 都带时间戳，点一下回到它在原声里被说出的那一秒 —— 这个服务器把同一批数据变成 可查的接口。

为什么需要它

站上本来就有 llms.txt / llms-full.txt，但那是给「整篇读一遍」准备的： llms-full.txt 有 6.9 MB，agent 要回答「谁讲过 reward hacking」只能把它整份读进 上下文。这个服务器让它先筛出几条，再按需要取那一集的结构。

装

不用装。只要有 Python 3.10+：

json
{  "mcpServers": {    "ourword": {      "command": "python3",      "args": ["/path/to/mcp/ourword_mcp.py"]    }  }}

只用标准库，没有第三方依赖。数据从线上取，所以不会拿到发行当天的旧快照。

四个工具

工具做什么
search_episodes按关键词、节目、分类找集
get_episode一集的要点／金句／数字／术语，每条带时间戳
list_shows在册节目，各自已深读多少篇、最新一篇是哪天
latest_episodes最近的深读，可按分类

关于原文

这里不提供逐字稿。 逐字稿是各播客的版权内容，站上任何一份文件里都没有， 这个接口也不会有。给出去的是我们自己写的判断、可核对的数字、带署名的短引用， 以及回到原音频那一秒的链接 —— 引用的人可以自己去核。

自建

bash
OURWORD_SITE=/path/to/your/checkout python3 ourword_mcp.py

Source: mcp/README.md at commit 688b1a7

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 21, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts