How to Use the Harvard WHO Health MCP in LangChain

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

Install langchain-mcp-adapters. Then use MultiServerMCPClient with the server URL. Call client.gettools() and pass them directly into your agent setup.

Q: Can LangChain agents search Harvard WHO Health indicators automatically?

Yes. Give the agent access to searchindicators. It will query the database for the right WHO codes before attempting to pull time-series data.

Q: Does Harvard WHO Health work with LangSmith tracing?

It does. Every call to tools like getimmunization or gettuberculosis registers as a discrete step in your LangSmith dashboard. You see exactly what the agent requested and what the MCP server returned.

Q: How do I handle state when querying multiple countries?

The server is stateless by default. Use client.session() in your script to maintain persistent context while looping through multiple ISO codes.

Q: How is data privacy handled when querying HIV statistics?

The server processes read-only requests for macro-level gethivaids prevalence percentages. No patient-level data exists in the WHO database. Your queries route through an ephemeral V8 Isolate Sandbox, meaning the parameters you search vanish the moment the connection closes.

Build multi-step global health pipelines with LangChain and real WHO data.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain WHO Health Data with LangChain

The `search_indicators` tool feeds directly into your LangChain ReAct agents to locate specific global health metrics. You pass a disease keyword, the agent grabs the indicator code, and immediately triggers `get_indicator_data` to pull the time-series values. This setup turns raw WHO statistics into automated research workflows. You can pipe the results of `get_health_expenditure` straight into a custom prompt template, forcing the agent to calculate cost-per-capita trends without you writing the glue code. LangSmith tracks every token and MCP Server call along the way.

Cross-Reference Disease Burden

The `compare_countries` tool lets your agent pull a decade of metrics for specific nations in a single execution. Your pipeline can grab ISO codes using `get_countries`, then iterate through regions to compare baseline health factors. You build the logic, and the MCP Server handles the data layer. If you want to correlate `get_water_sanitation` rates with `get_malaria` incidence in Sub-Saharan Africa, your agent executes both tools sequentially. The output of the first query dictates the parameters of the second.

Automate Epidemiological Research

The `get_mortality` tool accepts common indicator codes like NCDMORT3070 to pull non-communicable disease death rates. You can wire this up with `get_ncd` to create a continuous monitoring chain for specific health outcomes. Your agent decides the execution order based on the initial prompt. It might check `get_life_expectancy` first, notice an anomaly in a specific year, and automatically query `get_health_workforce` to see if a drop in physician density explains the shift.

Setup guide

Set up Harvard WHO Health MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Harvard WHO Health tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "harvard-who-health-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Harvard WHO Health transactions"
    })
    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 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 LangChain

Install `langchain-mcp-adapters`. Then use `MultiServerMCPClient` with the server URL. Call `client.get_tools()` and pass them directly into your agent setup.

Yes. Give the agent access to `search_indicators`. It will query the database for the right WHO codes before attempting to pull time-series data.

It does. Every call to tools like `get_immunization` or `get_tuberculosis` registers as a discrete step in your LangSmith dashboard. You see exactly what the agent requested and what the MCP server returned.

The server is stateless by default. Use `client.session()` in your script to maintain persistent context while looping through multiple ISO codes.

The server processes read-only requests for macro-level `get_hiv_aids` prevalence percentages. No patient-level data exists in the WHO database. Your queries route through an ephemeral V8 Isolate Sandbox, meaning the parameters you search vanish the moment the connection closes.

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