BioAI 日知

Official5 tools

by MInsYang · JavaScript

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

io.github.MInsYang/bioai-rizhi (MCP Server)

The io.github.MInsYang/bioai-rizhi MCP server provides read-only access to BioAI 日知. It exposes biopharma-related information, including news, research records, companies, and source status, based on the server’s described purpose.

🛠️ Key Features

Read-only access
Biopharma news retrieval
Research records access
Companies information access
Source status availability

🚀 Use Cases

Monitoring biopharma news from BioAI 日知
Reviewing and referencing research records
Looking up companies mentioned in BioAI 日知
Checking the status of data sources

⚡ Developer Benefits

Uses a stable, read-only model for data consumption
Supports structured use across news, records, companies, and source status

⚠️ Limitations

Restricted to read-only operations
Limited to the scope described: BioAI 日知 biopharma content

Topics

bioaicloudflare-workersmcporganoidsvirtual-cell

Captured live from the server via tools/list.

search_resources

Search stored public research abstracts and industry source records by keywords, topic, academic/industry category and time window. days=0 searches all stored dates. This tool searches source records; it does not claim they are editor-reviewed news.

Parameters9

language	string	optional	Optional presentation language. Omit for legacy copy. Source text remains in its original language.
query	string	optional
topic	string	optional
academic	string	optional
journal_tier	string	optional
company	string	optional
days	integer	optional
limit	integer	optional
offset	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "language": {
      "description": "Optional presentation language. Omit for legacy copy. Source text remains in its original language.",
      "type": "string",
      "enum": [
        "zh-CN",
        "zh-Hant",
        "en"
      ]
    },
    "query": {
      "default": "",
      "type": "string",
      "maxLength": 200
    },
    "topic": {
      "type": "string",
      "enum": [
        "virtual-cell",
        "organoid",
        "virtual-embryo",
        "virtual-organ",
        "drug-discovery"
      ]
    },
    "academic": {
      "default": "all",
      "type": "string",
      "enum": [
        "all",
        "academic",
        "industry"
      ]
    },
    "journal_tier": {
      "default": "selected",
      "type": "string",
      "enum": [
        "selected",
        "all"
      ]
    },
    "company": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "pattern": "^[a-z0-9][a-z0-9_-]*$"
    },
    "days": {
      "default": 30,
      "type": "integer",
      "minimum": 0,
      "maximum": 3660
    },
    "limit": {
      "default": 20,
      "type": "integer",
      "minimum": 1,
      "maximum": 40
    },
    "offset": {
      "default": 0,
      "type": "integer",
      "minimum": 0,
      "maximum": 10000
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

get_resource

Read one stored source record by UUID, or an editor-reviewed event when kind='event'. Returns up to 6000 characters of stored source text, original URLs, publication status and provenance. It never retrieves arbitrary external URLs.

Parameters3

language	string	optional	Optional presentation language. Omit for legacy copy. Source text remains in its original language.
id	string	required
kind	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "language": {
      "description": "Optional presentation language. Omit for legacy copy. Source text remains in its original language.",
      "type": "string",
      "enum": [
        "zh-CN",
        "zh-Hant",
        "en"
      ]
    },
    "id": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "kind": {
      "default": "record",
      "type": "string",
      "enum": [
        "record",
        "event"
      ]
    }
  },
  "required": [
    "id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

search_companies

Find directory companies by current or historical name, topic, track or region. Topic matches and directory metadata are discovery aids, not a complete market census or source verification certificate.

Parameters8

language	string	optional	Optional presentation language. Omit for legacy copy. Source text remains in its original language.
query	string	optional
topic	string	optional
track	string	optional
region_group	string	optional
history	boolean	optional
limit	integer	optional
offset	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "language": {
      "description": "Optional presentation language. Omit for legacy copy. Source text remains in its original language.",
      "type": "string",
      "enum": [
        "zh-CN",
        "zh-Hant",
        "en"
      ]
    },
    "query": {
      "default": "",
      "type": "string",
      "maxLength": 200
    },
    "topic": {
      "type": "string",
      "enum": [
        "virtual-cell",
        "organoid",
        "virtual-embryo",
        "virtual-organ",
        "drug-discovery"
      ]
    },
    "track": {
      "type": "string",
      "enum": [
        "测序与多组学",
        "生物医药",
        "AI与模型数据",
        "学术进展",
        "sequencing-multiomics",
        "biopharma",
        "ai-models-data",
        "academic-research"
      ]
    },
    "region_group": {
      "type": "string",
      "enum": [
        "cn",
        "hk",
        "global",
        "cross"
      ]
    },
    "history": {
      "default": false,
      "type": "boolean"
    },
    "limit": {
      "default": 20,
      "type": "integer",
      "minimum": 1,
      "maximum": 40
    },
    "offset": {
      "default": 0,
      "type": "integer",
      "minimum": 0,
      "maximum": 10000
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

get_company

Read one company directory profile with name/alias provenance, public source verification status and up to 20 published events. Official-website fields in directory metadata are not automatically verified sources.

Parameters2

slug	string	required
language	string	optional	Optional presentation language. Omit for legacy copy. Source text remains in its original language.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "pattern": "^[a-z0-9][a-z0-9_-]*$"
    },
    "language": {
      "description": "Optional presentation language. Omit for legacy copy. Source text remains in its original language.",
      "type": "string",
      "enum": [
        "zh-CN",
        "zh-Hant",
        "en"
      ]
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

get_source_status

Inspect a bounded page of publicly visible source verification/collection status and the current topic definitions. last_success_at reports successful source collection, not when every source was last updated. No credentials, configuration or internal error logs are returned.

Parameters5

language	string	optional	Optional presentation language. Omit for legacy copy. Source text remains in its original language.
query	string	optional
company	string	optional
limit	integer	optional
offset	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "language": {
      "description": "Optional presentation language. Omit for legacy copy. Source text remains in its original language.",
      "type": "string",
      "enum": [
        "zh-CN",
        "zh-Hant",
        "en"
      ]
    },
    "query": {
      "default": "",
      "type": "string",
      "maxLength": 200
    },
    "company": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "pattern": "^[a-z0-9][a-z0-9_-]*$"
    },
    "limit": {
      "default": 20,
      "type": "integer",
      "minimum": 1,
      "maximum": 40
    },
    "offset": {
      "default": 0,
      "type": "integer",
      "minimum": 0,
      "maximum": 10000
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

README.md8 KBView on GitHub

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

text

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。

Install

Tools (5)

search_resourcesget_resourcesearch_companiesget_companyget_source_status

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://bioai-rizhi.pages.dev/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "bioai-rizhi": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://bioai-rizhi.pages.dev/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.MInsYang/bioai-rizhi (MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

search_resources

get_resource

search_companies

get_company

get_source_status

BioAI 日知 · 问象

能做什么

部署架构

本地运行

数据与来源

验证

Install

Remote endpoint

Related servers