How to Use the USGS Earthquakes MCP in LangChain

Q: How can I use USGS Earthquakes and LangChain together to track historical data?

You'll use queryearthquakes to define a specific time window, like last year. The agent then processes the returned list of events, allowing you to analyze trends that simple single-tool calls miss.

Q: If I'm building a large system with USGS Earthquakes and LangChain, how is context managed?

You should use client.session() to maintain persistent context. This keeps the state of complex searches—like continually filtering results based on previous queries—across multiple tool calls.

Run Multi-Step Earthquake Analyses with LangChain's Reasoning 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 LangChain

Create your Vinkius account to connect USGS Earthquakes to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step Search Logic via MCP Server

Build complex reasoning pipelines that decide which tool to fire and in what order. You can start by using `get_significant_30_days` to flag recent high-impact events, then chain the results into a subsequent call to `query_earthquakes` to narrow the search area based on those initial coordinates. This agentic flow allows your AI client to perform sequential data validation. It's perfect for determining if a series of related quakes are geographically clustered or if they require individual analysis using `count_earthquakes`.

Dynamic Query Filtering with LangChain

You don't just run a single search; you build the criteria. Use parameters like minimum magnitude, time windows, and specific geographic boundaries inside `query_earthquakes`. The agent can dynamically adjust these inputs based on user chat history or prior tool outputs. For example, if the user asks for 'all major quakes last week,' your LangChain agent handles passing a calculated start/end time range to the server, ensuring the results are always scoped correctly.

Counting and Aggregating Earthquake Data

Sometimes you just need a number. The `count_earthquakes` tool lets your agent get the total count of seismic events matching specific criteria without pulling potentially massive datasets. This is fast, clean data for quick summaries. It's ideal when an analyst needs to quickly check if activity in a region has crossed a threshold—say, checking how many quakes hit above 4.5 magnitude this month. The agent reports the single integer result directly.

Setup guide

Set up USGS Earthquakes MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes USGS Earthquakes tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "usgs-earthquakes-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent USGS Earthquakes transactions"
    })
    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 LangChain

You'll use `query_earthquakes` to define a specific time window, like last year. The agent then processes the returned list of events, allowing you to analyze trends that simple single-tool calls miss.

The server provides real-time seismic and earthquake data. This includes event coordinates, magnitudes, and time stamps for every reported quake.

Absolutely. Since it's a framework designed for multi-server aggregation, you can combine seismic data with vector store lookups or database records in one continuous agentic workflow.

Yes. The server taps into the live USGS seismic network, providing near-real-time data for global monitoring and analysis using its specialized tools.

You should use `client.session()` to maintain persistent context. This keeps the state of complex searches—like continually filtering results based on previous queries—across multiple tool calls.

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