How to Use the NOAA Tides & Currents API MCP in Pydantic AI

Get type-safe, validated NOAA tidal data in your Python agent with Pydantic AI. No more corrupted data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NOAA Tides & Currents API MCP to Pydantic AI

Create your Vinkius account to connect NOAA Tides & Currents API 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 Tides & Currents API with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Prevent Data Corruption at Runtime

Here's the thing: APIs change. With Pydantic AI, your agent won't silently fail or process bad data if the NOAA API returns an unexpected field. Every response from `get_water_levels` or `get_tide_predictions` is automatically validated against a Pydantic model. If the data doesn't match the expected schema—say, a number comes back as a string—your agent will raise a `ValidationError` immediately. This forces you to handle the error instead of letting corrupted data flow through your system. It's about correctness, not just convenience.

Model-Agnostic Tools for your Pydantic AI Agent

You're not locked into a single LLM provider. Pydantic AI lets you use this NOAA toolset with OpenAI, Anthropic, Gemini, or even a local model. The tools just work. Your agent gets access to `get_air_temperature` and `get_water_temperature` regardless of the brain you plug in. This means you can switch your underlying model based on cost or performance without rewriting any of your tool-using logic. The MCP Server handles the connection to the NOAA API, and Pydantic AI handles the type-safe integration with your chosen agent.

Check Dependencies Before You Act

Good code checks its dependencies. Before your agent wastes time trying to pull a week's worth of tidal data, have it call `check_api_status` first. It's a simple, clean way to build reliability into your agent's logic. Because Pydantic AI structures everything so clearly, this becomes a natural first step in any function that needs to talk to the outside world. The response is a validated boolean, so there's no ambiguity. Your code knows for sure if the NOAA service is ready.

Setup guide

Set up NOAA Tides & Currents API 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-tides-currents-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NOAA Tides & Currents API 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 Tides & Currents. 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 Tides & Currents API 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 Tides & Currents API MCP in Pydantic AI

Pydantic AI automatically validates every API response from this MCP server against a predefined schema. If a tool like `get_water_levels` returns data in an unexpected format, a `ValidationError` is raised instantly, preventing your agent from using incorrect data.

Yes. Pydantic AI is model-agnostic. You can connect this MCP toolset to an agent running on a local model just as easily as one using a major cloud provider.

It lets your agent verify that the NOAA Tides & Currents API is online before attempting a data-intensive call like `get_tide_predictions`. This prevents unnecessary errors and makes your agent's behavior more predictable and robust.

No. Pydantic AI and the Vinkius MCP server handle it. You just call the tool, and you get back a clean, validated Pydantic object with the tidal data you asked for.

The only data transmitted is the non-sensitive query itself, like the station ID for `get_water_temperature`. Your LLM API keys and application code are never sent. Each request is handled in a dedicated, memory-safe V8 Isolate on Vinkius that is destroyed after your request completes.

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