How to Use the NOAA Marine — Tides, Currents & Coastal Data MCP in Pydantic AI

Q: How do I register NOAA Marine — Tides, Currents & Coastal Data in Pydantic AI?

Install the slim package with pip install "pydantic-ai-slimmcp". Then, define your toolset using MCPToolset pointing to your Vinkius HTTP endpoint, and pass it directly to the agent constructor.

Q: Does NOAA Marine — Tides, Currents & Coastal Data support runtime type checking in Pydantic AI?

Yes, every piece of telemetry returned by tools like getmeteorological is validated against Pydantic schemas. If a field fails validation, the framework raises a runtime error, preventing the agent from acting on corrupt data.

Enforce strict runtime type safety over NOAA marine telemetry using Pydantic AI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NOAA Marine — Tides, Currents & Coastal Data MCP to Pydantic AI

Create your Vinkius account to connect NOAA Marine — Tides, Currents & Coastal Data 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 NOAA Marine — Tides, Currents & Coastal Data with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe oceanographic data with Pydantic AI

`get_water_levels` pulls real-time coastal water heights and validates the response against strict Pydantic models before your agent sees them. This tool guarantees you never process malformed telemetry or corrupt station datums. If NOAA's API structure changes, your system fails loudly instead of passing garbage data downstream. Using Pydantic AI ensures that fields like water height and quality flags are typed correctly as floats and strings. You write cleaner agent logic because you do not have to manually parse or validate the incoming JSON.

Strict validation for marine current modeling

`get_currents` retrieves speed and direction measurements from specialized offshore current meters. This tool provides critical physical oceanography data for safe harbor navigation. Your agent uses these speed and direction values to calculate drift vectors safely. Because Pydantic AI validates these floats at runtime, you can trust that your navigational math is based on real physical telemetry.

Predicting tides reliably with this MCP Server

`get_tide_predictions` gives your agent the exact times and heights of upcoming high and low tides. This tool is crucial for planning coastal surveys or commercial fishing schedules. Combine these predictions with `get_water_temperature` to track thermal changes across tidal cycles. The framework validates both datasets simultaneously, preventing silent failures during complex multi-tool execution.

Setup guide

Set up NOAA Marine — Tides, Currents & Coastal Data 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": {
        "noaa-marine-tides-currents-coastal-data-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NOAA Marine — Tides, Currents & Coastal Data tools.",
)

result = await agent.run("List recent NOAA Marine — Tides, Currents & Coastal Data 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 NOAA. 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 NOAA Marine — Tides, Currents & Coastal Data 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 NOAA Marine — Tides, Currents & Coastal Data MCP in Pydantic AI

Install the slim package with `pip install "pydantic-ai-slim[mcp]"`. Then, define your toolset using `MCPToolset` pointing to your Vinkius HTTP endpoint, and pass it directly to the agent constructor.

Yes, every piece of telemetry returned by tools like `get_meteorological` is validated against Pydantic schemas. If a field fails validation, the framework raises a runtime error, preventing the agent from acting on corrupt data.

Absolutely. Pydantic AI is model-agnostic, meaning you can hook this server up to local models or commercial APIs while maintaining strict schema enforcement for tools like `get_sea_level_trends`.

It uses Streamable HTTP or SSE transports managed by Vinkius. This lets you run the MCP Server externally while your Python agent connects securely using a single endpoint token.

Yes, Vinkius handles all authentication and runs the MCP Server inside an ephemeral V8 sandbox. Your queries for water levels and tide predictions are processed in-memory and never stored or shared.

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