How to Use the Harvard WHO Health MCP in Pydantic AI

Q: How do I connect Pydantic AI to the Harvard WHO Health MCP Server?

You initialize the connection using the MCPToolset class with the server's HTTP URL. Pass this toolset directly into the Agent constructor to expose all 16 health indicator tools to your model.

Q: Does this server support Server-Sent Events transport in Pydantic AI?

Yes, you can connect using the SSE transport protocol. The MCPToolset class manages the connection lifecycle automatically, keeping your data pipeline stable.

Fetch type-safe WHO health datasets with Pydantic AI and validate every indicator payload at runtime.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate maternal and child health data in Pydantic AI

You extract precise maternal mortality ratios using `get_maternal_health` and `get_immunization` to ensure your Pydantic AI pipelines receive strictly typed inputs. The Pydantic AI framework validates the incoming JSON schema against your defined Python models at runtime, failing loudly if any WHO field is missing. This MCP Server guarantees structured responses for DTP3, measles, and polio vaccination coverage in Pydantic AI. Your agent processes these figures safely, knowing that any unexpected data format will trigger a validation error rather than corrupting your database.

Query structured environmental health metrics

You check clean water and hygiene access using `get_water_sanitation` to analyze regional development markers with Pydantic AI. Pydantic AI maps this tool to your agent, ensuring that the returned values for safely managed sanitation match your exact float and string types. By using the unified Pydantic AI `MCPToolset` class, you connect to the external MCP Server over a secure Server-Sent Events transport. Your agent queries the sanitation metrics and immediately feeds them into your local analysis models with zero type-casting friction.

Analyze global indicators with Pydantic AI

You explore detailed metadata structures using `get_dimensions` and `get_indicator_data` to break down metrics by sex and year in Pydantic AI. This MCP Server delivers clean time-series data that fits perfectly into your type-safe agent workflows. The Pydantic AI framework ensures that confidence intervals and country codes returned by `get_countries` conform to your validation schemas. You write clean Python code without defensive try-except blocks around every WHO API response.

Setup guide

Set up Harvard WHO Health MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

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

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Harvard WHO Health tools.",
)

result = await agent.run("List recent Harvard WHO Health transactions")
print(result.output)

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 Pydantic AI

You initialize the connection using the `MCPToolset` class with the server's HTTP URL. Pass this toolset directly into the `Agent` constructor to expose all 16 health indicator tools to your model.

The framework will raise a validation error at runtime if the payload doesn't match your Pydantic schemas. This prevents your agent from processing corrupted or hallucinated health metrics.

Yes, the framework is completely model-agnostic. You can run your agent with local models or commercial APIs while fetching structured data from the health server.

Yes, you can connect using the SSE transport protocol. The `MCPToolset` class manages the connection lifecycle automatically, keeping your data pipeline stable.

Your transactions for sanitation indices and medical staffing ratios run through disposable V8 runtime containers. We verify your endpoint token cryptographically, leaving zero traces of your health data queries on the hosted server.

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