MCP.Market

Ourword MCP server

by woowoeth·io.github.woowoeth/ourword·v1.0.0·1 stars

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

A88/100grade A
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

1 stars

Reviews

Write one

Nobody has reviewed Ourword yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Ourword tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it

no findings
  • –Code scanpackage could not be scannedn/a
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Ourword compares

Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 80% of 3,470 Web search servers
GitHub stars
1
more than 55% of 1,786 Web search servers

Install Ourword in Claude Code, Cursor or VS Code

The registry entry has no remote endpoint or installable package.

What the publisher says

From the Ourword repository's README, as published. We do not edit it. Read it on GitHub

原声 · 播客深读

世界太吵,来原声听播客。

每天从 54 档中英文播客里挑出值得记住的判断。要点和金句都带时间戳,点一下就回到

它在原声里被说出的那一秒;金句逐字校验过、数字回原文核对过——查不到出处的,

一律不上站。

线上: https://ourword.ai/podcast/ · RSS · 信源清单

为什么要重做一个

同类站点(如 onepod.site)的做法是:抓 21 个 YouTube 频道的自动字幕,让模型写一篇散记发出来。三个问题:

第三行是重点。这个仓库里没有"尽力而为"这个选项——pipeline/lib/gate.py 验不过的记录不会变成页面。

内容质量是怎么保证的

一、文稿五层回退(pipeline/lib/transcript.py)

按质量从高到低试,第一个通过密度校验的胜出:

  1. feed — 节目在 RSS 里发布的 (VTT / SRT / JSON)。Odd Lots、TBPN、Practical AI、Think Fast、Acquired 有。JSON 那种还自带说话人分离。
  2. notes — feed 条目本身就是全文。Substack 系(Latent Space、Interconnects)习惯把整份逐字稿贴进 content:encoded,格式是 Joon [00:31:12]: …,于是说话人归属和精确时间戳都是免费的。
  3. page — show notes 里的 transcript 链接,或节目页。抓下来必须通过标题特征词校验确认是这一集,否则丢弃(否则会抓到节目的归档页)。
  4. youtube — yt-dlp 拉自动字幕。会做滚动重复裁剪(YouTube 的字幕是"上一条尾部 + 新内容",直接拼接会把每句说两遍)。
  5. asr — 下载音频送 Whisper 兼容接口转写,带 segment 时间戳。长音频用 ffmpeg 切片。

每一层都要过语速校验:英文 70–300 wpm,中文 110–520 字/分。低于下限说明拿到的是 show notes 冒充逐字稿;高于上限说明抓错了文档。两种情况都当作"没有文稿"。

二、编辑质检(pipeline/lib/gate.py)

剔除了什么、为什么剔除,都写进 run log(Actions artifact 保留 14 天),页面侧栏也会显示"质检剔除 N 处"。

三、跨源去重

同一集经常同时出现在 RSS 和节目的 YouTube 频道。指纹 = 归一化标题 + 时长按 2 分钟分桶,命中就跳过。(对照站点没做这个,同一集出现过两次。)

事故记录

踩过的坑都在 POSTMORTEM.md,按错误类型分组,每条写清现象、根因、 以及现在靠什么防住。前三类各自重复发生过三到四次(失败却报成功、基础设施抖动被当成 内容缺失、校验规则误杀真内容),改这个项目之前值得先读一遍。

能自动化的都变成了检查:tests/test_guards.py 直接断言那些教训——推送重试循环必须 检查结果、评审失灵必须拦下而选题失灵必须放行、移除信源需连续失败(一次抖动不算)、 评分不许全挤在及格线上、理由与分数必须一致、信源 id 不许因中文名塌成 42/src、 字符串相似度四版失败用例全部保留、判据必须承认"判断与框架"这种价值形态、 每页恰好一个 h1、cron 还开着、本机脚本含提交推送。纯文档防不住重犯。

python3 -m unittest discover -s tests    # 87 项

怎么自动更新

有两条路,看你能不能拿到 key。

两条线同时在跑,分工由 IP 决定,互不重复:

state.json 在 git 里,本机跑前先 git pull,所以不会重复发同一集。

A · 本机定时(已装,不需要任何 key)

用本机已登录的 claude CLI 生成。不产生 API 账单,但会花 Claude 订阅额度, 所以刻意压小:每天 2 篇、模型 sonnet、跳过超过 2 万词的超长集,约 5 万 input tokens/天。

cp scripts/com.ourword.podcast.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.ourword.podcast.plist

每天 10:30 与 21:30 各跑一次(--only-residential,每次上限 6 篇),完整链路并推送。 日志在 .cache/logs/。停掉用 launchctl unload。代价:机器睡着或断网时不跑 (launchd 会在唤醒后补跑)。

转写用本机模型,不需要任何 key:mlx-whisper(Apple Silicon)+ imageio-ffmpeg 自带的静态 ffmpeg。它返回逐句真实时间码,比云端 SenseVoice 那条更准(后者只给整段 文本,得按字数插值)。~/.config/podcast/env 里若放了 LLMAPIKEY 就走 API 账单, 否则回退到本机 claude CLI(会花订阅额度,因此刻意压小篇数并用 sonnet)。

B · GitHub Actions 云端日更(需要一个 key,当前定时已停用)

.github/workflows/daily.yml 的 cron 已注释掉——没有可用 key 时开着只会天天 红灯。拿到 key 后取消注释即可。不限 Anthropic:任何 OpenAI 兼容端点都行, 配三个 secret 就跑:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Ourword: common questions

Is Ourword MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Ourword safety report
Does Ourword need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Ourword maintained?
The last commit was 4 days ago (2026-10-31). The latest release is v1.0.0.
What can I use instead of Ourword?
Servers from other publishers that do the same job: screenpipe MCP server and AIHOT MCP server.
How does Ourword compare with other Web search MCP servers?
safety score 88/100 (higher than 80% of 3,470 Web search servers); github stars 1 (more than 55% of 1,786 Web search servers). Full comparison.

Alternatives to Ourword

Same job from other publishers: the closest match first, then the best rated.

  • screenpipe
    Search your local screen recordings, audio transcripts, and computer activity from screenpipe.
    B
  • AIHOT
    Chinese AI news: search topics, explore hot events, and read daily, weekly and monthly briefs.
    B