How to Use the USGS Earthquakes MCP in AutoGen

Negotiate Complex Earthquake Scenarios with AutoGen's Consensus Agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect USGS Earthquakes MCP to AutoGen

Create your Vinkius account to connect USGS Earthquakes to AutoGen 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 USGS Earthquakes with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Search Parameters via MCP Server

AutoGen agents don't just execute; they argue over the best way to query. You can set up an agent pair where one challenges the other on search criteria. One might suggest using `get_significant_30_days` for a broad look, while another argues that specific filtering via `query_earthquakes` is needed. The agents negotiate until they agree on the optimal parameters (magnitude, time range) to pass to the MCP Server, resulting in a consensus query.

Consensus-Driven Data Aggregation with AutoGen

You need to know the total count of quakes *and* their locations. Instead of one tool call, multiple agents debate which tools are necessary (`count_earthquakes` vs. `query_earthquakes`) and what parameters must be used in both. The final output is a synthesized conclusion based on all inputs. This simulates real-world decision-making where an incident report requires input from several specialized perspectives.

Multi-Agent Verification of Earthquake Events

Run three agents: one for location checks, one for magnitude analysis, and a third for temporal consistency. The system only moves forward when all agents agree on the event's validity using data from `query_earthquakes`. This built-in deliberation adds layers of reliability. This is critical when dealing with complex, multi-source data like global seismic activity.

Setup guide

Set up USGS Earthquakes MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes USGS Earthquakes tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="USGS Earthquakes_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent USGS Earthquakes data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="USGS Earthquakes_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent USGS Earthquakes data")
    print(result.messages[-1].content)

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 USGS. 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 USGS Earthquakes 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 USGS Earthquakes MCP in AutoGen

You can set up agents that debate the criteria for reporting. One agent might check if the event is significant enough, while another uses `query_earthquakes` to confirm its location against historical data.

The server provides real-time seismic and earthquake data. AutoGen's framework allows multiple agents to iteratively test different tool calls and parameters against that live stream of data until a consensus is reached.

Yes. Since the server draws from the established USGS seismic network, it provides verifiable source material for your multi-agent decision-making process.

The framework is designed for conflict resolution. Agents debate competing hypotheses—for example, one agent might flag an event as high risk while another reports low activity count, forcing deliberation.

The core data type is seismic and earthquake data. Specifically, the server provides structured records detailing location, magnitude, time, and count of events.

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