How to Use the WHO GHO MCP in AutoGen

Q: Do I need specific codes for WHO GHO with AutoGen?

Yes, when pulling detailed metrics, you must use searchwhoindicators first. This ensures the agents are working with valid indicator codes before running getwhoindicatordata.

WHO GHO MCP Server: Simulate debates on global health metrics with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WHO GHO MCP to AutoGen

Create your Vinkius account to connect WHO GHO to AutoGen 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 WHO GHO with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Data Interpretation Across Agents

Agents can use `search_who_indicators` to gather a set of relevant indicators needed for debate. Once the initial data is collected, agents can argue over which metrics are most important. This allows you to simulate consensus-driven decision making—for instance, one agent might focus on mortality while another challenges it using immunization coverage data.

Validate Country Profiles in Group Discussion

`get_who_country_profile` provides a quick health snapshot for comparison. You can set up agents to debate the best course of action by comparing two countries' profiles side-by-side. One agent might argue that country A is better due to its profile, while another challenges that conclusion based on available environmental data.

Challenge Assumptions with Specific Metrics

`get_who_indicator_data` returns highly specific metrics broken down by year and sex. Agents can use this depth to challenge simple conclusions. Instead of accepting a single number, you force the agents to debate *why* that metric is trending up or down over time for a given country.

Setup guide

Set up WHO GHO MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes WHO GHO tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="WHO GHO_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent WHO GHO data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="WHO GHO_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent WHO GHO data")
    print(result.messages[-1].content)

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. 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 WHO GHO 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 WHO GHO MCP in AutoGen

You pass the tool list to your AssistantAgent, letting multiple agents debate and challenge each other's conclusions based on real-time data calls. The user gets a consensus decision, not just a single answer.

Absolutely. You can set up two agents—one focused on Country A and one on Country B—and have them argue over which country has the better health outcome using `get_who_country_profile`.

The server handles global health indicator data. This allows your multi-agent system to discuss complex topics like disease prevalence and life expectancy across multiple regions.

Yes, when pulling detailed metrics, you must use `search_who_indicators` first. This ensures the agents are working with valid indicator codes before running `get_who_indicator_data`.

This MCP Server supports any framework that allows multi-agent interaction. You connect it to Vinkius, making the live data available for deliberation among your agents.

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