How to Use the USGS Water Services MCP in LangChain

Q: Can I query groundwater levels using USGS Water Services with LangChain?

Yes. You'll use getgroundwaterlevels. The agent needs specific filters—like a site ID and date range—to execute the tool call, ensuring you get accurate historical manual readings.

Build complex water data pipelines with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect USGS Water Services MCP to LangChain

Create your Vinkius account to connect USGS Water Services 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 Water Services with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain together multi-step queries.

Need to find out the mean streamflow for a site and then use that data to look up historical groundwater levels? You can chain these calls together. Start by calling `get_instantaneous_values` with specific filters, and then pass those results directly into `get_groundwater_levels`. This builds a precise, multi-step reasoning pipeline. Your agent decides which tool runs next based on the output of the previous one. It's perfect for complex data analysis where the answer isn't obvious—it requires multiple steps using tools like `get_daily_values` and `get_sites` in sequence.

Find site metadata and statistics.

Before you analyze anything, you gotta know what data exists. The agent can first use `get_sites` to search for a list of USGS locations based on multiple filters (like state code AND county). Once it has the IDs, it runs `get_statistics` to pull annual or monthly summaries. This process is solid for planning. You get the site metadata first, then you calculate yearly averages using `get_statistics`. It's a repeatable workflow that keeps your whole chain grounded in verifiable USGS data.

Get near real-time water readings.

Getting immediate flow rates is simple. You pass filters—like a specific site and state code—to the `get_instantaneous_values` tool, and your agent runs it immediately. This gives you the latest 15-minute interval measurements for streamflow or other parameters. If you need to compare that instant reading against a longer trend, the chain can automatically call `get_daily_values`, using the site ID from the first step. It's fast and handles both immediate reads and historical context in one flow.

Setup guide

Set up USGS Water Services 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 Water Services 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-water-services-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 Water Services 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 Water Services. 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 Water Services 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 Water Services MCP in LangChain

You build a multi-step agent that calls the MCP Server. For example, you can first call `get_sites` to find metadata for specific locations, and then pass those location IDs into `get_instantaneous_values`. The chain manages this flow automatically.

You can set up the agent to iterate through state codes. It calls `get_daily_values` for each state, aggregates the results in memory, and gives you a unified report without needing separate code blocks.

Yes. You'll use `get_groundwater_levels`. The agent needs specific filters—like a site ID and date range—to execute the tool call, ensuring you get accurate historical manual readings.

Absolutely. You can combine multiple major filters for almost every tool. For instance, `get_instantaneous_values` lets you filter by sites, stateCd, and countyCd all at once.

The server accesses structured historical and near real-time water data. All calls are managed through an endpoint token provided by Vinkius, keeping your usage secure.

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