How to Use the GDACS MCP in Mastra AI

Q: Can my Mastra AI agent react differently to red vs. orange GDACS alerts?

Absolutely. After calling getalerts, use Mastra's conditional branching. You can define a workflow path for 'red' alerts that triggers an immediate escalation, and a different path for 'orange' alerts that just logs the event.

Q: Is it possible to add a human approval step to a GDACS workflow in Mastra AI?

Yes, that's a core Mastra feature. Use requireToolApproval in your agent's definition. For instance, your agent can fetch impact data with getimpacts from GDACS, but it must wait for your approval before taking action based on that data.

Q: What's the best way to search for specific disasters?

Use the geteventlist tool. It lets you filter by event type, like VO for volcanoes or WF for wildfires, and also by date range.

Build resilient disaster response workflows on Mastra AI using real-time triggers from the GDACS server.

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 Mastra AI

Create your Vinkius account to connect GDACS to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Conditional Disaster Workflows

Mastra AI is built for logic. You can build a workflow that polls `get_alerts` every five minutes. If it finds a 'red' alert, it automatically triggers a sequence: first, call `get_event_detail` to get the specifics, then use `get_impacts` to assess the damage. Mastra's strength is what happens next. If the estimated economic loss from `get_impacts` is over a certain threshold, your workflow can automatically escalate the issue. If the API call fails, it retries with exponential backoff. This isn't just a query; it's a reliable, automated process.

Build Fault-Tolerant Monitoring with Mastra AI

Don't let a dropped connection stop your monitoring. Set up a Mastra AI agent to periodically call `get_latest_cyclones` or `get_latest_earthquakes`. Mastra's built-in engine will handle retries automatically if the GDACS API is temporarily unavailable. You can also add a `requireToolApproval` step for sensitive actions. For example, before acting on a `get_impacts` report, the workflow can pause and wait for a human to confirm, adding a manual check to your automated MCP server system.

Chain GDACS Tools for Deeper Insight

A simple query isn't enough. With Mastra AI, you can chain calls together to build a complete picture. Start with `get_event_list` to find all recent wildfires, loop through each one to call `get_event_detail`, and then fetch `get_event_geojson` to map the burn area. This creates a robust data pipeline. Each step is a tool call, and Mastra manages the state and logic between them. It turns a series of simple API calls into a sophisticated analysis workflow.

Setup guide

Set up GDACS MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All GDACS tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "gdacs-mcp-client",
  servers: {
    "gdacs-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "GDACS Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to GDACS tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent GDACS transactions"
);
console.log(result.text);

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 Mastra AI

Use Mastra's workflow engine to schedule calls to tools like `get_latest_floods`. Mastra's automatic retries mean your agent won't fail if there's a temporary network issue connecting to the GDACS MCP server.

Absolutely. After calling `get_alerts`, use Mastra's conditional branching. You can define a workflow path for 'red' alerts that triggers an immediate escalation, and a different path for 'orange' alerts that just logs the event.

Yes, that's a core Mastra feature. Use `requireToolApproval` in your agent's definition. For instance, your agent can fetch impact data with `get_impacts` from GDACS, but it must wait for your approval before taking action based on that data.

Use the `get_event_list` tool. It lets you filter by event type, like `VO` for volcanoes or `WF` for wildfires, and also by date range.

The connection from your Mastra AI agent is proxied through Vinkius's secure environment. The only data transmitted to GDACS are the specific tool calls, like a request for `get_latest_droughts` details. The logic of your workflow and the disaster data you retrieve remain isolated within your agent's execution context.

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