How to Use the FEMA MCP in Google ADK

Q: Can I join FEMA grant data with BigQuery using Google ADK?

Yes, your agent can fetch historical records using gethazardmitigationgrants and write them directly to BigQuery. This lets you run SQL queries on fresh federal data within your Google Cloud project.

Analyze massive federal disaster datasets using Google ADK and Gemini's million-token context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FEMA MCP to Google ADK

Create your Vinkius account to connect FEMA to Google ADK 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 FEMA with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ingest massive FEMA grant histories into Google ADK

The `get_hazard_mitigation_grants` tool feeds long-term infrastructure funding histories directly into Gemini's massive context window via our MCP Server. Google ADK lets your agent pull thousands of historical grant records in a single call, bypassing the need for complex vector databases. Once the raw data is loaded, your agent can analyze decades of regional mitigation trends. It connects this stream directly to your enterprise Vertex AI models for deep pattern matching.

Map emergency agencies to BigQuery tables

The `get_emergency_agencies` tool extracts state-level emergency contact lists directly through your Google ADK agent. This allows your agent to cross-reference real-time federal contact directories with your internal BigQuery logistics tables. By combining these sources, your agent can automatically update contact records in your Google Cloud databases. It ensures your field operations teams always have verified local agency contacts during a crisis.

Scale emergency intelligence with an MCP Server

The `get_public_assistance_applicants` tool exposes public assistance applicant data to your Gemini models via our managed MCP Server. Google ADK handles the HTTP transport natively, letting you restrict tool access with simple filters. Your enterprise agents can now cross-verify active applicant lists without manual API integrations. This setup keeps your cloud architecture clean while maintaining a direct pipeline to federal disaster response records.

Setup guide

Set up FEMA MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with FEMA tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="FEMA_agent",
    model="gemini-2.0-flash",
    instruction="You have access to FEMA tools via MCP.",
    tools=mcp_tools,
)

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 FEMA. 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 FEMA 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 FEMA MCP in Google ADK

Use the McpToolset class with our streamable HTTP URL to expose the MCP Server to your LlmAgent. You can optionally restrict the toolset to only expose specific endpoints like `get_fema_regions`.

Yes, your agent can fetch historical records using `get_hazard_mitigation_grants` and write them directly to BigQuery. This lets you run SQL queries on fresh federal data within your Google Cloud project.

The framework uses Gemini's long-context window to process large payloads from `get_disaster_applications` in a single pass. This minimizes the need for complex pagination logic in your code.

Yes, you can pass a list of specific tool names to your McpToolset instance. This prevents the agent from calling endpoints like `get_individuals_program` if you only want it analyzing regional structures.

All communications with the federal API are routed through zero-trust, ephemeral network tunnels. Your public assistance applicant records are processed entirely in memory and never written to persistent storage, satisfying strict enterprise compliance standards on Google Cloud.

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