How to Use the GDACS MCP in Claude Code

Q: How do I write a bash script with Claude Code to check GDACS for new wildfires?

In your script, use the command claude mcp call gdacs-mcp getlatestwildfires. You can pipe the output to jq to check if the burnedarea exceeds a certain threshold, and if so, send an alert.

Q: Can I use Claude Code and GDACS to get a quick summary of an event from my terminal?

Yes. Just run claude mcp call gdacs-mcp geteventdetail --eventid . You'll get a clean JSON response in your terminal with the event's name, type, magnitude, and other key details without needing to open a browser.

Q: How do I filter GDACS event lists by date range using Claude Code?

The geteventlist tool accepts startdate and enddate parameters in YYYY-MM-DD format. Your command would look like this: claude mcp call gdacs-mcp geteventlist --eventtype EQ --startdate 2023-01-01 --enddate 2023-01-31.

Q: How do I connect Claude Code to the GDACS server?

It's a single command in your terminal: claude mcp add --transport http gdacs-mcp -- . Once added, you can verify the connection with claude mcp list. The configuration is stored locally in /.claude.json.

Pipe real-time GDACS disaster data directly into your CI/CD pipelines, cron jobs, and shell scripts with Claude Code.

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 Claude Code

Create your Vinkius account to connect GDACS to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Gate Deployments Based on Live Alerts

Use the GDACS server to build automated safety checks right into your deployment pipeline. A simple shell script can ask Claude Code to run `get_alerts` and check for red alerts in a specific region before allowing a production deploy to proceed. If a major earthquake (`EQ`) or cyclone (`TC`) is detected near your data center's location, the script can fail the build. This is how you connect real-world events to your infrastructure automation.

Run Headless Monitoring Scripts

You don't need a UI for this. Set up a cron job that runs a command every five minutes: `claude mcp call gdacs-mcp get_latest_earthquakes --min_magnitude 6.0`. Pipe the JSON output to another script that triggers a PagerDuty alert. This is a completely server-side, headless monitoring system built with a few lines of bash. It's reliable, simple, and lives where your other infrastructure tools do: the terminal.

Automate Data Extraction for Your ETL MCP Server

This MCP server is perfect for batch jobs. Write a script that tells Claude Code to fetch all floods from the past year with `get_event_list`, then pipes the list of event IDs to a second command that loops through them, calling `get_impacts` for each. The output is clean, structured JSON, ready to be piped into `jq` for transformation or loaded directly into a database. It's a straightforward way to pull specific disaster data for offline analysis or reporting.

Setup guide

Set up GDACS MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see gdacs-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest GDACS transactions." It will automatically discover and invoke the available GDACS tools.

Terminal

claude mcp add --transport http gdacs-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the GDACS MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "gdacs-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

In your script, use the command `claude mcp call gdacs-mcp get_latest_wildfires`. You can pipe the output to `jq` to check if the `burned_area` exceeds a certain threshold, and if so, send an alert.

Yes. Just run `claude mcp call gdacs-mcp get_event_detail --event_id `. You'll get a clean JSON response in your terminal with the event's name, type, magnitude, and other key details without needing to open a browser.

The `get_event_list` tool accepts `start_date` and `end_date` parameters in YYYY-MM-DD format. Your command would look like this: `claude mcp call gdacs-mcp get_event_list --event_type EQ --start_date 2023-01-01 --end_date 2023-01-31`.

It's a single command in your terminal: `claude mcp add --transport http gdacs-mcp -- `. Once added, you can verify the connection with `claude mcp list`. The configuration is stored locally in `~/.claude.json`.

The connection is stateless. Your pipeline sends requests for public GDACS disaster data—like event IDs or country codes—and gets a JSON response. No part of your infrastructure's configuration, secrets, or code is ever sent to the MCP server.

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