BioAI Daily MCP
Bring research and industry information with traceable sources into your AI.
Connect to your AI
Choose a client, copy the configuration, then check that the tools have loaded.
Public MCP endpoint
https://bioai-rizhi.pages.dev/mcp
Use this endpoint in an MCP client that supports Streamable HTTP. The public service needs no login or API key. Check connection status and tool availability in your client.
Once the public endpoint is published, this page will provide its address and client configurations. You can also deploy your own service from the source package below.
MCP connects tools to your AI client. Add the public endpoint, then confirm that your client discovers the tools.
Choose your client and copy the configuration
codex mcp add bioai --url https://bioai-rizhi.pages.dev/mcp
codex mcp listRun the commands in your terminal, then start or reopen a Codex session. Use /mcp to see the loaded tools. If a configuration with this name already exists, check its endpoint first. OpenAI documentation ↗
claude mcp add --transport http bioai --scope user https://bioai-rizhi.pages.dev/mcp
claude mcp get bioai--scope user saves the connection to your user configuration. Reopen Claude Code and use /mcp to check connection status and tools. These commands are for the Claude Code terminal client. Claude Code documentation ↗
{
"mcpServers": {
"bioai": {
"url": "https://bioai-rizhi.pages.dev/mcp"
}
}
}Merge this into your user ~/.cursor/mcp.json or project .cursor/mcp.json, keeping your existing server configurations. Save, reload as Cursor prompts, and check the tools in MCP settings. Cursor documentation ↗
Run your own service
Run the website, MCP and collection queue in your Cloudflare account, connected to your Neon database.
View deployment stepsTools and responses
Five public tools use the same read scope as the website. Use them to organize research leads, explore companies and check source coverage.
| Tool | What it does | Inputs |
|---|---|---|
search_resources | Find research and industry leadsSearch source records collected by the site, with publication dates, original links and classifications. | Keyword · Topic · Date |
get_resource | Read a record and its sourceRead a source record or published event, then follow the original link to check it. | Record or event ID |
search_companies | Explore a field through companiesSearch the company directory by name, topic and region. | Company · Topic · Region |
get_company | Explore a companyRead company details, alias verification status, public sources and published events. | Company slug |
get_source_status | Understand coverage and freshnessCheck public source verification and collection status, along with topic and journal policies. | Source · Company · Coverage |
Information comes with its evidence limits. Search covers content already collected by the site, and results retain their sources and status. Source records, company entries and published events have distinct meanings. Preprint status, automated classifications and coverage information help you assess the material. The interface supports 简体中文, 繁體中文 and English. Use the language parameter to choose the language of MCP explanations; news, papers and evidence excerpts retain their original source text.
Language selection in tool arguments:language accepts zh-CN / zh-Hant / en.
Try a prompt
Example prompt
Set language="en" when calling the tools. Find research leads on AI virtual cells from the past 30 days. Keep the DOI, preprint status and original links. Check source status first, then explain this site’s coverage limits.
Company insightsFind companies in the organoid topic. Distinguish physical platforms from AI models and list sources I can check.
Coverage checkCheck collection status for the relevant sources and explain what a week without new results could mean.
Deploy your own service
Your deployment runs the website, API and MCP service in your Cloudflare account, connected to your database and collection queue. MCP provides public read access to the service.
The Worker serves the website and MCP and consumes the Queue. Pages can forward requests to the Worker through a Service Binding. Collection, review and public reads share one data model.
Get the maintained source
Start with the project’s Cloudflare implementation branch and install dependencies from the lockfile.
git clone --branch codex/bioai-resource-site https://github.com/MInsYang/bioai-rizhi.git cd bioai-rizhi npm ci --prefix cloudflare/siteInitialize your service using the deployment guide
Configure the Queue, Neon database, migrations and Worker in your account. Follow the current guide to set runtime variables and secrets such as
DATABASE_URLandADMIN_TOKEN, then run the build checks and deploy.Use the appropriate steps for database initialization, service upgrades and historical data recovery. The source seed initializes the directory and source configuration.
Verify, then connect your AI
Check service health, real data reads, source status and calls to all five MCP tools. Add
/mcpto your deployed HTTPS address and use it in place of the URL in the “Connect to the public service” examples.Verify the connection through tool discovery and a real read. Saving a configuration or opening the website alone does not confirm a working connection.
Collection freshness and coverage depend on sources, scheduling and runtime status. Check Cloudflare, Queue and Neon capacity and costs against your account plans.