How to Use the Harvard WHO Health MCP in Mastra AI

Build resilient backend workflows that analyze WHO health data using Mastra AI's fault-tolerant agent framework.

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 Mastra AI

Create your Vinkius account to connect Harvard WHO Health to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Public Health Reporting

Set up a workflow that runs on a schedule to gather fresh health data. Your Mastra AI agent can call `get_countries`, then loop through the list to pull the latest numbers for `get_malaria` and `get_tuberculosis` for each one. If a request to the underlying WHO API fails, Mastra's engine automatically retries with exponential backoff. This means your data gathering jobs actually finish instead of failing due to a transient network blip. It's built for jobs that can't fail.

Build Conditional Alert Systems

Your agent can do more than just fetch data; it can make decisions. Create a workflow that regularly checks `get_mortality` for a specific cause in a key country. If the number crosses a threshold you define, the workflow can branch. From there, it could trigger other tools to gather context—like `get_health_workforce` or `get_health_expenditure`—before formatting a detailed notification and sending it to a Slack channel or logging a ticket. Mastra handles the if/then logic for you.

Resilient Data Extraction with this MCP Server

Stop writing custom retry logic for data extraction scripts. Use a Mastra AI workflow to pull a large set of indicators using `get_indicator_data`. The agent will systematically work through the list, and the built-in workflow engine handles any API rate limits or connection drops. This is perfect for back-office tasks like populating a data warehouse or generating a weekly analytical report. You define the steps, and Mastra ensures the process runs to completion, handling failures gracefully along the way.

Setup guide

Set up Harvard WHO Health MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Harvard WHO Health tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "harvard-who-health-mcp-client",
  servers: {
    "harvard-who-health-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Harvard WHO Health Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Harvard WHO Health tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Harvard WHO Health transactions"
);
console.log(result.text);

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 Mastra AI

Absolutely. You can create a scheduled workflow in Mastra AI that calls a tool like `get_ncd` for diabetes prevalence. The workflow can store the result and compare it to the previous run, triggering another action if the value changes.

Mastra AI has automatic retries with exponential backoff built into its workflow engine. If a call to a tool like `get_hiv_aids` fails due to a temporary issue, Mastra will try again automatically before marking the step as failed.

You'd build a multi-step workflow. The first step could use `search_indicators` to find all relevant metrics. Subsequent steps would then loop through those indicator codes and call `get_indicator_data` for your target country.

The tools themselves are single-operation, but you can easily create a batch process in Mastra. Your workflow can iterate through a list of countries or indicators, calling the MCP tools like `get_indicator_data` for each item in the loop.

The server deals strictly with public World Health Organization statistics, not sensitive user data. Vinkius provides a zero-trust environment where each agent's request is isolated and authenticated, ensuring your workflow's integrity.

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