How to Use the WHO Athena API MCP in CrewAI

Q: Can I ensure all WHO Athena API calls are authorized using CrewAI?

Yes, you use toolfilter when setting up the MCP connection. This lets your crew select only specific tools—like gethealthindicatordata—and hide the rest from the agents to enforce security.

Autonomous Global Health Analysis with WHO Athena API via CrewAI Agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WHO Athena API MCP to CrewAI

Create your Vinkius account to connect WHO Athena API 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 WHO Athena API with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Data Reporting

Assign the `get_health_indicator_data` tool to a specialized 'Analyst' agent. This agent researches specific global statistics using WHO indicator codes, then hands that structured data off to another agent for interpretation. The collaboration allows you to build an autonomous reporting process where one agent fetches raw metrics, and the next processes them without human intervention.

Autonomous Metadata Discovery

Use a 'Research' agent with `list_health_indicators` and `list_health_dimensions`. This allows the crew to automatically map out all available data fields needed for a comprehensive report. The agents identify metadata requirements first. This is crucial for setup. Before attempting retrieval, one specialized agent confirms what variables (like country or year) are even possible in the WHO database.

Monitoring API Health Checks

A dedicated 'Monitor' agent can run `check_api_status` as part of its routine. This ensures that every autonomous operation starts with a confirmation that the underlying WHO service is live. The monitoring agent watches sessions, immediately escalating if the status check fails, preventing wasted computation time.

Setup guide

Set up WHO Athena API 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 WHO Athena API tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent WHO Athena API 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="WHO Athena API Analyst",
        goal="Access and analyze WHO Athena API data via MCP.",
        backstory="Expert analyst with direct WHO Athena API access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent WHO Athena API 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 Athena. 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 Athena API 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 Athena API MCP in CrewAI

You pass the MCP Server URL directly to your Agent definitions. The 'Crew' then manages sequential execution: one agent calls `list_health_indicators`, passes that list, and another agent uses it with `get_health_indicator_data`.

It handles global health indicator data. The tools provide the raw metrics and the necessary metadata (like dimensions and indicators) that specialized agents need to collaborate on a report.

Yes, you use `tool_filter` when setting up the MCP connection. This lets your crew select only specific tools—like `get_health_indicator_data`—and hide the rest from the agents to enforce security.

This server touches global health indicator data. All retrieved data are structured metrics tied to indicators and dimensions, which requires careful management of access scope within your crew's memory.

The four available tools cover the full lifecycle: discovery (`list_health_indicators`), validation (`check_api_status`), and retrieval (`get_health_indicator_data`). This gives your crew everything it needs to operate autonomously.

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