How to Use the Harvard WHO Health MCP in LlamaIndex

Q: How do I set up Harvard WHO Health with LlamaIndex?

Run pip install llama-index-tools-mcp. Initialize BasicMCPClient, wrap it with McpToolSpec, and call totoollistasync(). Pass that list directly to your FunctionAgent.

Q: Can LlamaIndex filter the available Harvard WHO Health tools?

Yes. You can use the allowedtools parameter to restrict access. If your RAG app only needs mortality data, just expose getmortality and getlifeexpectancy.

Q: Does Harvard WHO Health support includeresources for LlamaIndex?

It does. Setting includeresources=True allows the MCP client to read the underlying data schemas. This helps the indexing engine structure the WHO statistics correctly.

Q: How do I find specific disease codes for my RAG application?

Provide the searchindicators tool to your agent. It will search the 1000+ WHO indicators and find the exact code needed before executing the data retrieval step.

Q: Are my queries about non-communicable diseases stored?

No. When your RAG app calls getncd to pull diabetes or obesity rates, the request hits a zero-trust endpoint. Vinkius manages the authentication, and the query parameters are wiped immediately after the JSON response is delivered.

Index global health metrics directly into your LlamaIndex vector stores.

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 LlamaIndex

Create your Vinkius account to connect Harvard WHO Health to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground RAG Apps in WHO Health Data

The `get_indicator_data` tool pulls raw time-series statistics that LlamaIndex instantly converts into searchable document nodes. Your RAG application queries the API, retrieves the historical data, and embeds it right next to your internal policy PDFs. This stops your agent from hallucinating health statistics. When a user asks about regional funding, LlamaIndex pulls exact purchasing power figures from `get_health_expenditure` instead of guessing. The MCP Server acts as a live data pipeline for your vector store.

Index LlamaIndex MCP Server Metadata

The `get_dimensions` tool helps your indexing engine understand how to disaggregate complex health data. Your setup reads the metadata first, learning exactly how indicators are split by sex, age, or region before running the main query. You use `McpToolSpec` to expose these capabilities. The agent learns the structure of the WHO database dynamically. It knows to use `get_countries` to validate ISO codes before attempting to embed regional data into the index.

Embed Disease Prevalence Trends

The `get_maternal_health` tool returns mortality rates per 100,000 live births. LlamaIndex takes this structured output and makes it semantically searchable for your policy analysts. You can combine multiple data streams. Feed `get_tuberculosis` incidence rates and `get_immunization` coverage into a unified index. Users can then ask natural language questions and get answers backed by hard WHO data points.

Setup guide

Set up Harvard WHO Health MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Harvard WHO Health MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Harvard WHO Health tools.",
)
response = await agent.run("List recent Harvard WHO Health data")

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 LlamaIndex

Run `pip install llama-index-tools-mcp`. Initialize `BasicMCPClient`, wrap it with `McpToolSpec`, and call `to_tool_list_async()`. Pass that list directly to your `FunctionAgent`.

Yes. You can use the `allowed_tools` parameter to restrict access. If your RAG app only needs mortality data, just expose `get_mortality` and `get_life_expectancy`.

It does. Setting `include_resources=True` allows the MCP client to read the underlying data schemas. This helps the indexing engine structure the WHO statistics correctly.

Provide the `search_indicators` tool to your agent. It will search the 1000+ WHO indicators and find the exact code needed before executing the data retrieval step.

No. When your RAG app calls `get_ncd` to pull diabetes or obesity rates, the request hits a zero-trust endpoint. Vinkius manages the authentication, and the query parameters are wiped immediately after the JSON response is delivered.

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