How to Use the Harvard WHO Health MCP in OpenAI Agents SDK

Get raw WHO health data directly into your OpenAI Agents SDK pipeline with built-in guardrails and zero-config tool discovery.

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 OpenAI Agents SDK

Create your Vinkius account to connect Harvard WHO Health to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Compare multi-country health trends safely

You query ten years of epidemiological data across multiple nations using `compare_countries` to feed your OpenAI Agents SDK multi-agent analysis. This framework maps the health query directly to your agent's execution context, letting specialized agents hand off tasks when comparing regional health outcomes. Your OpenAI Agents SDK system executes these `compare_countries` queries with strict validation guardrails before the API call is made. You monitor every single WHO data fetch on the OpenAI developer dashboard, ensuring your public health model never hallucinated historical metrics.

Track infectious disease metrics via OpenAI Agents SDK

You monitor global infection rates by calling `get_tuberculosis`, `get_malaria`, and `get_hiv_aids` through your OpenAI Agents SDK network. This MCP Server exposes these specialized endpoints so your OpenAI agent can pull specific country-level disease counts without parsing messy health reports manually. By setting the `cacheToolsList=True` parameter in your Python configuration, you avoid redundant discovery lookups during high-frequency OpenAI Agents SDK analysis. Your agents instantly know which infectious disease tools are available, keeping response times low during critical WHO data runs.

Map population health and funding variables

You connect financial inputs to physical outcomes using `get_health_expenditure` and `get_life_expectancy` to find correlations between spending and longevity in the OpenAI Agents SDK. This MCP Server lets your agent pull exact purchasing-power-adjusted spending alongside raw mortality tables. The OpenAI Agents SDK manages the HTTP connection stream cleanly behind the scenes. You pass the server instance directly into the Agent constructor, allowing your model to decide exactly when to check funding levels versus when to query life expectancy metrics.

Setup guide

Set up Harvard WHO Health MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Harvard WHO Health tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Harvard WHO Health tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Harvard WHO Health tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Harvard WHO Health Agent",
            instructions="You have access to Harvard WHO Health tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the agents package and pass the server URL into the `MCPServerStreamableHttp` constructor. Then, add the resulting server instance to your agent's `mcp_servers` list to enable automatic tool discovery.

You configure tool access by defining specific system prompts or wrapping the server initialization in a custom agent handler. This prevents your agents from calling tools like `get_water_sanitation` if they only need to analyze `get_immunization` data.

The SDK relies on standard HTTP backoff mechanisms when the server rate limits your queries. You can monitor these API calls and their latency directly from your OpenAI developer dashboard.

Yes, you initialize the server connection using an async context manager in Python. This allows your agents to fetch tuberculosis and malaria datasets concurrently without blocking your main execution thread.

All requests for global health indicators and disease statistics are processed inside isolated, single-tenant V8 sandboxes. Your authentication token is verified instantly, and no raw health data is ever retained on our servers.

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