How to Use the Harvard WHO Health MCP in CrewAI

Deploy autonomous agent crews on CrewAI to research, analyze, and report on global health trends from 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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Public Health Research Crew

Delegate complex research tasks to a specialized crew of agents. Assign a 'Researcher Agent' to use `search_indicators` to discover all metrics related to water quality. It then passes the list of indicator codes to an 'Analyst Agent'. The Analyst Agent takes those codes and systematically calls `get_water_sanitation` and `compare_countries` for a specified list of nations. Finally, a 'Writer Agent' takes the structured data from the analyst and drafts a summary report. Each agent does its job, and you get the final result.

Run Autonomous Outbreak Monitoring

Build a crew that acts as a perpetual monitoring system. One agent's job is to run on a schedule, checking `get_malaria` and `get_tuberculosis` data for high-risk regions. It does nothing but watch the numbers. If that agent detects a statistically significant spike, it triggers a second 'Investigator Agent'. This new agent's task is to gather context by pulling related data, like `get_health_workforce` and `get_immunization` coverage for that area, before escalating the complete findings.

Multi-Agent Comparative Analysis

Use a crew to perform deep comparative analysis that would be tedious for a human. For example, a 'G7 Specialist Agent' could be tasked with pulling a dozen key health indicators, from `get_life_expectancy` to `get_health_expenditure`, for all G7 countries. Simultaneously, a 'BRICS Specialist Agent' does the same for BRICS nations. Both agents complete their work and save it to a shared context. A final 'Synthesizer Agent' then accesses all the data and generates a report comparing the two economic blocs. This is the power of an MCP Server in a multi-agent setup.

Setup guide

Set up Harvard WHO Health MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Harvard WHO Health tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Harvard WHO Health Analyst",
    goal="Access and analyze Harvard WHO Health data via MCP.",
    backstory="Expert analyst with direct Harvard WHO Health access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Harvard WHO Health transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Harvard WHO Health Analyst",
        goal="Access and analyze Harvard WHO Health data via MCP.",
        backstory="Expert analyst with direct Harvard WHO Health access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Harvard WHO Health transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can assign different tools from this MCP server to different agents. For instance, give one agent `search_indicators` to find data, and another agent `get_indicator_data` and `compare_countries` to perform the analysis.

Yes. CrewAI allows each agent in a crew to have its own set of tools. One agent can be using `get_mortality` while another is using `get_ncd`, and they can share their findings to collaborate on a task.

Assign one agent the role of 'Researcher' and give it exclusive access to the `search_indicators` tool. This agent's sole job is to take natural language queries from other agents (or you) and return the correct, machine-readable WHO indicator codes.

Yes, that's the primary model for using CrewAI with an MCP server. An 'Analyst' agent can fetch data using tools like `get_life_expectancy`, then pass its numerical findings to a 'Writer' agent that drafts a narrative report.

The server provides access to public WHO health statistics, ensuring no private data is ever at risk. Vinkius runs each MCP server in a sandboxed, single-use instance, and authenticates every call from your CrewAI agents with a dedicated token.

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