How to Use the Harvard WHO Health MCP in Cursor

Q: What's the best way to set up the Harvard WHO Health MCP server in Cursor for my team?

Create a .cursor/mcp.json file in your project's root directory and add the Harvard WHO Health server configuration there. Commit that file to your Git repository, and everyone on the team will have the same tools.

Q: Is it possible to get raw time-series data from Harvard WHO Health inside Cursor?

Yes, that's what getindicatordata is for. You give it an indicator code and a country code, and it returns the raw time-series data, including year, value, and confidence intervals, right into your chat or code.

Stop mocking data. Code your health analytics app in Cursor with live WHO statistics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harvard WHO Health MCP to Cursor

Create your Vinkius account to connect Harvard WHO Health to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Harvard WHO Health with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Code with Live WHO Data

The Cursor agent can use `get_life_expectancy` to fetch data for a list of countries and then generate the Python script to plot it. This isn't a stub or a placeholder. The agent calls the tool, gets a real JSON response, and writes functional code that uses the actual data. This completely changes how you build. You're not just writing code that you *hope* will work with the API. You're building and testing against the live data structure from the first line, which catches errors and saves hours of debugging.

Test Your Analysis Against Real Stats

You're building a model to predict health outcomes. Use the agent to call `get_mortality` for non-communicable diseases and `get_ncd` for obesity prevalence. You get real, historical data to feed directly into your local script. This creates a tight feedback loop right inside your editor. You can validate a hypothesis, adjust your model, and re-run it against actual WHO numbers in minutes. No more switching between your editor, a notebook, and an API client.

Look Up Country Codes and Data in Editor

Stop breaking your flow to look up country codes in a browser. Just ask the agent to use `get_countries` to get the ISO codes you need. Then, use those codes in a subsequent command to `compare_countries` or check `get_immunization` coverage. This MCP Server handles the API calls so you can stay focused on writing code. Let the agent manage fetching and formatting the data, while you focus on the logic that uses it. It's a smarter way to work with external APIs.

Setup guide

Set up Harvard WHO Health MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Harvard WHO Health MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Harvard WHO Health transactions." If the MCP tools are loaded correctly, Cursor will call the Harvard WHO Health tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "harvard-who-health-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by WHO GHO. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Harvard WHO Health now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Harvard WHO Health MCP in Cursor

Activate Agent mode and ask it to do it for you. For example: "Get tuberculosis data for Brazil using `get_tuberculosis` and write a Python script with Matplotlib to chart it." The agent will generate the code with the real data.

Absolutely. You can instruct the agent to "find the indicator code for child mortality," and it will use `search_indicators`. Then you can tell it to use that code with `get_indicator_data` to fetch the time-series for your application.

Create a `.cursor/mcp.json` file in your project's root directory and add the Harvard WHO Health server configuration there. Commit that file to your Git repository, and everyone on the team will have the same tools.

Yes, that's what `get_indicator_data` is for. You give it an indicator code and a country code, and it returns the raw time-series data, including year, value, and confidence intervals, right into your chat or code.

Yes. Your requests only contain non-sensitive information like WHO indicator codes and country names. All communication with the Vinkius-hosted server is encrypted, and the server itself operates within a zero-trust architecture, so your development environment is never directly exposed.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript