How to Use the GDACS MCP in CrewAI

Q: How can I set up a CrewAI team to process GDACS alerts?

Create a 'Monitor' agent that calls getalerts. If it finds a high-priority alert, it passes the event to an 'Analyst' agent. The Analyst then uses tools like getimpacts and geteventdetail from the GDACS server to gather intelligence.

Q: How do I give my CrewAI agents access to only specific GDACS tools?

When defining your agent in CrewAI, use the toolfilter option with the MCPServerHTTP class. This lets you expose only certain tools—like getlatestearthquakes—to a specific agent, enforcing role specialization.

Q: Can a CrewAI agent monitor multiple types of disasters at once?

Definitely. A single agent can be tasked with calling getlatestearthquakes, getlatestcyclones, and getlatestfloods in sequence. Or, for better design, have one agent call geteventlist and delegate analysis based on the event type (EQ, TC, FL).

Deploy autonomous agent crews with CrewAI to monitor, analyze, and respond to global disasters using GDACS data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GDACS MCP to CrewAI

Create your Vinkius account to connect GDACS 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 GDACS with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

The Autonomous Monitoring Crew

With CrewAI, you build teams. Assign one agent the role of 'Global Monitor'. Its only job is to periodically run `get_alerts` and `get_event_list` from the GDACS MCP server. It's simple, focused, and runs continuously. When the Monitor agent detects a new 'red' or 'orange' alert, it passes the event ID to the next agent in the crew. This separation of concerns is what makes CrewAI powerful. One agent watches, another thinks.

Create an Agent to Analyze Disaster Impact

Create a second agent, the 'Impact Analyst'. This agent receives event IDs from the Monitor agent. Its job is to use `get_event_detail`, `get_impacts`, and `get_event_geojson` to build a complete dossier on the disaster. This Analyst agent can calculate the proximity of the event to your company's assets using the GeoJSON data. It then synthesizes a report and passes its findings—estimated casualties, economic loss, and geographic footprint—to the final agent in the chain.

Let an Agent Decide the Next Action with CrewAI

The final agent in your crew is the 'Response Coordinator'. It takes the structured report from the Analyst and decides what to do. Its entire purpose is action, based on the intelligence gathered by its teammates. For example, if the Analyst reports high impact on a key logistics hub, the Response Coordinator can be programmed to automatically trigger your internal alerting systems or create a high-priority ticket. This is fully autonomous, end-to-end incident management.

Setup guide

Set up GDACS 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 GDACS tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent GDACS 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 GDACS. 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 GDACS 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 GDACS MCP in CrewAI

Create a 'Monitor' agent that calls `get_alerts`. If it finds a high-priority alert, it passes the event to an 'Analyst' agent. The Analyst then uses tools like `get_impacts` and `get_event_detail` from the GDACS server to gather intelligence.

Yes, that's a perfect use case. Create an agent whose primary tool is `get_event_geojson`. It can take an event ID and its sole job is to return a risk assessment based on the proximity of the disaster's GeoJSON footprint to your own list of locations.

When defining your agent in CrewAI, use the `tool_filter` option with the `MCPServerHTTP` class. This lets you expose only certain tools—like `get_latest_earthquakes`—to a specific agent, enforcing role specialization.

Definitely. A single agent can be tasked with calling `get_latest_earthquakes`, `get_latest_cyclones`, and `get_latest_floods` in sequence. Or, for better design, have one agent call `get_event_list` and delegate analysis based on the event type (`EQ`, `TC`, `FL`).

The communication between your agents happens within your CrewAI environment. The connection to the GDACS server is a direct, stateless call for data like `get_alert_detail`, handled by Vinkius. The disaster alert and impact data you pull is for your agents' use only; it isn't stored or monitored by our platform.

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