Bring Hydrology
to Pydantic AI
Learn how to connect USGS Water Services to Pydantic AI and start using 5 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the USGS Water Services MCP Server?
Connect to the USGS Water Services to retrieve comprehensive hydrological data directly from the United States Geological Survey. Monitor environmental conditions, analyze historical trends, and discover monitoring stations through natural language.
What you can do
- Real-time Monitoring — Use
get_instantaneous_valuesto fetch near real-time data (15-minute intervals) for streamflow, water levels, and quality. - Historical Analysis — Retrieve daily summaries (mean, median, max, min) using
get_daily_valuesfor long-term trend analysis. - Site Discovery — Search for monitoring stations using
get_sitesfiltered by state, county, hydrologic unit (HUC), or geographic bounding box. - Statistical Reports — Generate daily, monthly, or annual statistics with
get_statisticsto understand hydrological patterns. - Groundwater Tracking — Access specialized groundwater level data using
get_groundwater_levelsfor aquifer monitoring.
How it works
- Subscribe to this server
- This service accesses public USGS data; simply enter 'PUBLIC' as your access key to initialize
- Start querying water data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Environmental Scientists — quickly gather field data and historical records for research and reporting
- Engineers & Hydrologists — monitor streamflow and groundwater levels for infrastructure and flood planning
- Outdoor Enthusiasts — check real-time river conditions for fishing, boating, or safety before heading out
Built-in capabilities (5)
You MUST provide at least one major filter. Retrieve historical summarized daily data (mean, median, max, min)
You MUST provide at least one major filter. Retrieve historical manually-recorded groundwater levels
You MUST provide at least one major filter: sites, stateCd, huc, bBox, or countyCd. Retrieve near real-time water data (usually 15-minute intervals)
Multiple major filters can be combined (AND logic). Search for USGS sites and metadata
Retrieve daily, monthly, or annual statistics based on approved data
Why Pydantic AI?
Pydantic AI validates every USGS Water Services tool response against typed schemas, catching data inconsistencies at build time. Connect 5 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your USGS Water Services integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your USGS Water Services connection logic from agent behavior for testable, maintainable code
USGS Water Services in Pydantic AI
USGS Water Services and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect USGS Water Services to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for USGS Water Services in Pydantic AI
The USGS Water Services MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 5 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
USGS Water Services for Pydantic AI
Every tool call from Pydantic AI to the USGS Water Services MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I find all water monitoring sites in a specific state?
Use the get_sites tool and provide the 2-digit USPS state code (e.g., 'CA' for California) in the stateCd parameter. This will return a list of sites and their metadata for that state.
Can I get real-time streamflow data for a specific river station?
Yes! Use get_instantaneous_values with the specific USGS site number in the sites parameter. You can also specify parameterCd as '00060' for discharge (streamflow).
Is it possible to retrieve long-term monthly averages for a site?
Absolutely. Use the get_statistics tool with the statReportType set to 'monthly'. This will provide approved statistical summaries based on the historical record of the site.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your USGS Water Services MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Flexport
12 toolsManage global freight shipments, purchase orders, and logistics documents via AI agents with Flexport.
Fitbit
14 toolsAccess Fitbit health data via AI — query activities, sleep, heart rate, SpO2, body weight, and nutrition logs in natural conversation.
Lightspeed Restaurant
10 toolsManage restaurant orders, menus, tables, employees, payments, and revenue reports for your Lightspeed POS through natural conversation.
Cheddar
8 toolsManage usage-based billing and subscriptions via Cheddar — track usage, monitor invoices, and manage customers directly from any AI agent.