How to Use the USGS Water Services MCP in Pydantic AI

Q: How do I reliably get daily values with USGS Water Services using Pydantic AI?

You use getdailyvalues, making sure to provide a major filter. Since the response is validated, you'll know exactly what metrics (mean, min, max) are present for that historical date range.

Q: Can Pydantic AI handle complex site searches with USGS Water Services?

Yes. getsites allows combining multiple filters (e.g., bBox AND stateCd). The resulting list of sites will always adhere to the predefined Pydantic schema, making it easy for your agent to use.

Q: Does USGS Water Services support annual statistics with Pydantic AI?

It does. Use getstatistics and specify 'annual' as the timeframe. The returned data will be validated, so you never have to worry about unexpected or missing aggregate fields.

Ensure data correctness: USGS Water Services with Pydantic AI for validated MCP responses.

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 Pydantic AI

Create your Vinkius account to connect USGS Water Services to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate site metadata using `get_sites` on the MCP Server.

Start by calling `get_sites` to search for location data. This tool accepts multiple filters—you can combine state, HUC, and county codes in a single request. Because every response is validated against Pydantic models, you'll get predictable fields. No more running into unexpected or null metadata attributes.

Validate near real-time flow with `get_instantaneous_values`.

`get_instantaneous_values` pulls 15-minute intervals of water data. Use a filter like site code to target specific readings. If the underlying API sends back malformed or incomplete data, your agent fails loudly with a validation error. You'll know immediately when the reading is bad.

Validate historical groundwater levels using `get_groundwater_levels`.

Get manually recorded groundwater history via `get_groundwater_levels`. This tool requires specific parameters to define the scope of the retrieval. Type-safety means that when your agent processes these readings, it's guaranteed that the data structure matches what you expect. Zero silent corruption.

Setup guide

Set up USGS Water Services MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "usgs-water-services-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to USGS Water Services tools.",
)

result = await agent.run("List recent USGS Water Services transactions")
print(result.output)

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 Pydantic AI

You use `get_daily_values`, making sure to provide a major filter. Since the response is validated, you'll know exactly what metrics (mean, min, max) are present for that historical date range.

Yes. `get_sites` allows combining multiple filters (e.g., bBox AND stateCd). The resulting list of sites will always adhere to the predefined Pydantic schema, making it easy for your agent to use.

It does. Use `get_statistics` and specify 'annual' as the timeframe. The returned data will be validated, so you never have to worry about unexpected or missing aggregate fields.

The server touches streamflow (instantaneous and daily), historical groundwater levels, and site metadata. The data types are strictly defined by the schema, ensuring correctness.

The server touches publicly available hydrological measurements: streamflow metrics, groundwater levels, and site metadata. The primary benefit here is structural integrity; you're validating the *form* of the public data.

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