Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words
Beginner mode On
ColoursSystemLightDark
LanguageไทยEnglish中文日本語한국어EspañolDeutsch
☰ MenuSettings
Beginner mode On
ColoursSystemLightDark
LanguageไทยEnglish中文日本語한국어EspañolDeutsch

BioAI 日知

by MInsYangversion 3.2.0i★ –iRuns in the cloud
Registry nameio.github.MInsYang/bioai-rizhi

Install

Overview

Description from the maker (original English)

Read-only AI biopharma news, research records, companies, and source status from BioAI 日知.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Runs in the cloud
  • Transport: Streamable HTTP
  • Category: Search & AI memory

Install

Pick the AI app you use, then copy the settings.

Before you install

  • Basic checks: 1 of 1 passed
  • Runs on the maker’s server: what you ask it goes through their server.
  • The registry lists no key to fill in.

You need

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Works in Claude on the web, desktop and mobile:

  1. Open Settings → Connectors
  2. Press Add custom connector
  3. Paste the address below and press Add
  4. If it asks you to sign in, sign in with the maker
SettingsConnectors1+ Add2https://…3
https://bioai-rizhi.pages.dev/mcp

Run this in your terminal

claude mcp add --transport http bioai-rizhi https://bioai-rizhi.pages.dev/mcp

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "bioai-rizhi": {
      "url": "https://bioai-rizhi.pages.dev/mcp"
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "bioai-rizhi": {
      "type": "http",
      "url": "https://bioai-rizhi.pages.dev/mcp"
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

ChatGPT connects only to servers on the internet:

  1. Open ChatGPT on the web → Settings → Connectors (Apps)
  2. Press Create or Add (some plans need Developer mode under Advanced first)
  3. Paste the address below, give it a name and save
  4. If it asks you to sign in, sign in with the maker
SettingsConnectors1+ Create2https://…3
https://bioai-rizhi.pages.dev/mcp

Menu names can differ slightly by plan and over time.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

We have not read this server’s tool list yet; we check endpoints in rotation.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account MInsYang, which owns the repo

  • … Not checked yet

    Still maintained

    We have not read this repo from GitHub yet

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • … Not checked yet

    Endpoint responds

    Not checked yet; we check endpoints in rotation

  • … Not checked yet

    Sign-in with OAuth

    Not checked yet; we check endpoints in rotation

  • … Not checked yet

    No hidden instructions in tool descriptions

    Not checked yet; we read the tool list when we check the endpoint

Compared with others in Search & AI memoryi

  • More stars than 0% of the other 7247 servers in this category
  • Published to the registry more recently than 56% of the other 7247 servers in this category
  • Basic checks equal to or better than 100% of the other 7247 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is BioAI 日知 safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.

Is it still maintained?

The GitHub repo last changed –, and the latest version (3.2.0) reached the registry 29 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.

What can I use instead?

In the same category: Context7, Codebase Memory, Exa

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Context7

by upstash

Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.

Computer or cloud★ 64,224MITUpdated today
Install

Codebase Memory

by DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

Runs on your computer★ 48,148MITUpdated 20 days ago
Install

Exa

by exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

Runs in the cloud★ 5,213MITUpdated last month
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

BioAI 日知 · 问象

聚焦 AI 虚拟细胞、类器官、虚拟胚胎、虚拟器官、AI 药物发现 的研究与产业资源站。新闻文章、公司黄页、学术进展、产业时间线、合作关系图和来源状态共用 PostgreSQL；保留问象原 Logo 和统一导航。

3.2 统计与搜索版（2026-10-08）： 管理员可查看网页浏览、匿名会话、点击和 MCP 实际工具执行；新增有来源的专题指南、本周收录概要与分页 sitemap。每小时采集、每日摘要、问象报纸首页和手机/PC 布局保持整合。统计口径见 使用统计，搜索入口与验证边界见 搜索建设；当前部署验收见 统计验收 和 搜索验收。

访问 BioAI 日知，公开源码在 MInsYang/bioai-rizhi，默认分支为 codex/bioai-resource-site。MCP 地址为 https://bioai-rizhi.pages.dev/mcp；当前验收与待观察项目见 统计验收、搜索验收 和 TODO。已登记到官方 MCP Registry，见 接入与登记说明。

能做什么

  • 管理员统计看板：PV、匿名会话、点击、MCP 真实执行与耗时；支持 1/7/30 天，排除测试与已识别网页机器人，不补造历史流量。
  • 有原始出处的专题指南、本周收录概要，Google 网站验证与 sitemap 提交，每日 08:35 IndexNow 变更通知。
  • 报纸式头版与四个栏目导读；行业消息、合作与布局优先，学术作为研究依据。
  • 五个专题的真实原文检索、来源链接、发表/收录日期；学术默认 17 期刊白名单加 AI 相关性，历史预印本仅在明确选择全部存档后检索。
  • 国内外公司目录、官网、中英文及历史别名；包括新格元、寻因、诺禾致源。地区依据所在地/布局，不推断内外资股权。
  • 后台来源归属、社交账号验证、原文证据定位、事件复核和明确合作关系录入。Hot 图只显示附有证据的已发布关系。
  • 正式配置仅保留每小时第 7 分钟检查来源、北京时间 08:00 生成日报，无分钟诊断任务；小时派发链路已实测通过，手动日报接口和小时补偿实现已验证，每日专用回调尚未跨日观察。网页在有人使用时每 5 分钟检查新数据，闲置两分钟后暂停。
  • 公开只读 MCP，提供文章检索、文章详情、公司搜索、公司档案、来源状态五项工具；网站内有“连接你的 AI”页面。
  • 按主题 RSS、可分享的文章/公司/专题页、日报、sitemap、结构化网页信息与 llms.txt；本机关注 JSON 导入/导出。
  • 行业候选自动发现、证据复核后发布；每日 09:23 北京时间加密备份并在 GitHub 临时 PostgreSQL 17 恢复验证，保留 7 天。

类器官和器官芯片可能属于实体生物模型，不自动称为 AI。虚拟胚胎检索保留计算模型与实验胚胎模型的区别。原文收录、主题标签、来源验证、编辑核验和同行评议分别标识。

部署架构

浏览器 / RSS / MCP 客户端

↓ Cloudflare Pages 短域名 → Service Binding → Worker + Static Assets ↓ Neon PostgreSQL（公司、来源、原文、证据、事件、任务） ↑ Cron → Cloudflare Queue → 单页采集 → 保存检查点

数据库任务带租约令牌、主机限流、失败退避、重复记录去重及来源撤销检查。队列丢失的到期任务可由下一轮派发恢复。采集适配器采用来源域名白名单、响应大小和超时限制；公司主页发现仍可通过本地 Python 工具运行。

Cloudflare 免费账户并非只能有一个网站，无需为本项目删除 ResearchHub。免费配额、上线步骤、成本与生产验收见 Cloudflare 部署说明 和 运维手册。不保证任意流量和内容规模都能免费运行。

本地运行

需要 Node.js 24+、Python 3.12+、PostgreSQL 17。测试账号需能创建独立测试数据库；测试拒绝远程数据库。

python3 -m venv .venv

.venv/bin/python -m pip install -r backend/requirements.lock npm ci --prefix cloudflare/site cp .env.example .env

设置本地 DATABASE_URL 和至少 32 字符的 ADMIN_TOKEN

.venv/bin/python scripts/manage.py migrate .venv/bin/python scripts/manage.py seed .venv/bin/python scripts/configure_focus.py --backfill .venv/bin/python scripts/import_focus_supplement.py --apply .venv/bin/python scripts/configure_industry.py --apply --import-candidates node cloudflare/site/local.mjs

打开 http://127.0.0.1:8788/。后台位于 /#admin；管理员令牌仅保存在页面内存。local.mjs 使用真实 Worker 处理器和本地 PostgreSQL，其内存队列仅用于验收，不是生产调度器。

真实网络采集验收：

node cloudflare/site/local.mjs --ingest

若网络必须经过已配置的环境代理，Node 24+ 可加 --use-env-proxy。结果写入 docs/cloud-ingestion-e2e.json。抓取内容进入原文库，不能自动成为已核验新闻。不要同时启动旧 Python worker 和新的云端 consumer。

可选的 FastAPI 自托管模式保留在 backend/、deploy/，旧 HMAC 派发器保留在 cloudflare/dispatcher/；新云端方案使用 cloudflare/site/，不同时部署两套定时器。

数据与来源

原始任务书和两份不可替代的种子文件位于 docs/bootstrap；基础种子有 130 个实体。补充目录单独保存核验证据，原始种子文件保持不变。公司登记数量不等于已接入来源数量。

上线时将真实本地数据库恢复到新建的 Neon Free 项目（Singapore / aws-ap-southeast-1，PostgreSQL 17）空库：133 家公司、4,669 条 raw_items、4,012 条 public_resources；迁移 001–008 校验和核对通过。这是恢复验收时的计数，后续采集可能改变条数。

当前使用 PubMed、Europe PMC、Crossref 精选期刊元数据，以及公司官方 RSS 和限定路径的 Newsroom HTML。首轮与本轮云端状态分别保留，详见 期刊验证、行业来源审计 和 本轮验收。Tahoe 旧 RSS 的云端重试预算耗尽，现已停用云调度并保留历史真实原文；bioRxiv 直连仍停用。预印本不进入默认精选学术版。

public_resources 按明确的 PMID / DOI 去重已索引论文；不同预印本记录与原始版本信息仍保留。来源被撤销后，网站、RSS、日报和 MCP 的读取门槛同步生效。问象 Logo 见 品牌资产记录。

验证

.venv/bin/python -m pytest backend/tests -q

node tests/test_ui.cjs BIOAI_TEST_LOCAL=1 npm test --prefix cloudflare/site npm run check --prefix cloudflare/site

GitHub Actions 使用独立 PostgreSQL 17 服务运行检查，不依赖生产凭据。单元测试使用模拟边界条件；端到端抓取调用真实上游并写入本地 PostgreSQL。Wrangler dry-run 只验证构建，不等于生产部署或免费 CPU 额度验收。

本轮 JavaScript、Python、UI 契约及真实生产验证结果见 验收记录。Wrangler 构建、SDK 实测、Cloudflare 原生队列、跨日运行与费用样本分别报告，不能互相替代。个人 Codex 已配置短域名 MCP，其他客户端按接入文档配置。持续运行及长期免费容量仍需观察。

  • 首次补录结果 / 六来源增量结果
  • MCP 接入说明
  • 官方 MCP SDK 客户端验收
  • 生产验收记录
  • 资源站价值与推广建议
  • 上线缺口与真实来源清单
Ask PopNx