How to Use the USGS Water Services MCP in AutoGen

Run consensus decision making on USGS Water Services with AutoGen.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate optimal water data filters.

Imagine you need to know the best way to query for streamflow. You can set up multiple agents: one performance agent pushes for speed (calling `get_instantaneous_values`), while a security agent checks for historical accuracy (running `get_daily_values`). The agents debate which filter parameters are safest and fastest. They negotiate the best combination of inputs—like combining site codes from `get_sites` with date ranges for `get_statistics`—to converge on one optimal tool call.

Collaborative data retrieval using USGS Water Services.

Need to check groundwater levels, but the ideal parameters are unclear? You can run a multi-agent conversation. One agent might suggest `get_groundwater_levels` while another challenges it by requiring confirmation from the site metadata provided by `get_sites`. The system doesn't just execute; it deliberates. It forces consensus on which tools to use and in what order, making sure every data point is challenged before being accepted.

Automated analysis pipeline.

You can build a workflow where one agent fetches near real-time values via `get_instantaneous_values`. A second agent takes that output and automatically calls `get_statistics` to provide the historical context. This sequence requires coordination. The agents work together, debating if the current reading is an outlier compared to the annual average provided by `get_statistics`, giving you a fully reviewed conclusion.

Setup guide

Set up USGS Water Services 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 Water Services 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 Water Services_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent USGS Water Services 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 Water Services_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent USGS Water Services 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 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 AutoGen

You set up multiple specialized agents. For example, one agent might be the 'Data Validator' that calls `get_sites`, and another is the 'Forecaster' that uses those results to call `get_daily_values`.

Yes. The agents can debate which combination of filters (like bBox AND stateCd) is necessary for the most reliable data retrieval using tools like `get_instantaneous_values`.

It's better because it mimics human deliberation. Instead of blindly running a function, the agents challenge assumptions and negotiate the final set of parameters needed to call the MCP Server.

The adapter handles schema conversion automatically. You pass the tool list, and the underlying system manages how the input arguments for tools like `get_statistics` are passed between agents.

The server provides access to structured historical and near real-time water data. The security agent in your setup can even be configured to flag potential usage risks before any tool is called.

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