How to Use the NRC ADAMS (Nuclear Regulatory) MCP in Pydantic AI

Q: Can I use Pydantic AI to parse XML feeds from the NRC ADAMS (Nuclear Regulatory) server?

Yes, the output of getnrcrssfeed is parsed and validated against your defined Pydantic models. This ensures your agent only acts on structured, clean data from the nuclear event stream.

Q: How do I initialize the toolset in my Python application?

Use the MCPToolset class pointing to your Vinkius HTTP endpoint. This MCP Server handles connection over secure SSE, and you pass the toolset instance directly into your Agent's toolsets parameter.

Validate nuclear regulatory filings and live feeds at runtime using Pydantic AI and our type-safe 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 NRC ADAMS (Nuclear Regulatory) MCP to Pydantic AI

Create your Vinkius account to connect NRC ADAMS (Nuclear Regulatory) 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 NRC ADAMS (Nuclear Regulatory) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Live Reactor Feeds at Runtime

The `get_nrc_rss_feed` tool fetches real-time reactor status updates and regulatory notifications directly into your Pydantic AI agent. The framework validates every incoming feed item against strict Pydantic schemas, ensuring your pipeline never processes malformed data. If the Nuclear Regulatory Commission modifies their feed structure, your agent fails loudly and immediately. This strict validation prevents silent failures in your monitoring software, keeping your safety tracking systems reliable.

Enforce Type Safety on Legacy ADAMS Searches

The `search_adams_legacy` tool queries historical safety documents using a complex query structure that is prone to formatting errors. Pydantic AI uses runtime validation to ensure the generated parameters conform to the exact types expected by the legacy API. This type safety is critical because the legacy endpoint is retiring in June 2026. By validating the query inputs before transmission, you avoid sending broken requests to an aging regulatory database.

Connect Pydantic AI to Vinkius MCP Server

The `search_adams_legacy` tool operates inside a secure V8 isolate sandbox on Vinkius, serving as your remote MCP link. You connect your agent using the unified `MCPToolset` class, which handles the underlying SSE communication. This setup gives you a single, secure endpoint that handles all authentication behind the scenes. Your type-safe agents query public nuclear records while maintaining strict isolation.

Setup guide

Set up NRC ADAMS (Nuclear Regulatory) 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": {
        "nrc-adams-nuclear-regulatory-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NRC ADAMS (Nuclear Regulatory) tools.",
)

result = await agent.run("List recent NRC ADAMS (Nuclear Regulatory) 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 NRC ADAMS. 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 NRC ADAMS (Nuclear Regulatory) 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 NRC ADAMS (Nuclear Regulatory) MCP in Pydantic AI

The framework validates the search parameters before calling `search_adams_legacy`. If your agent generates an invalid query format, Pydantic AI raises a validation error immediately rather than executing a broken API call.

Yes, the output of `get_nrc_rss_feed` is parsed and validated against your defined Pydantic models. This ensures your agent only acts on structured, clean data from the nuclear event stream.

The framework will raise a runtime validation error, preventing your agent from hallucinating or propagating corrupted regulatory data. This is crucial for safety-critical applications where accuracy is mandatory.

Use the `MCPToolset` class pointing to your Vinkius HTTP endpoint. This MCP Server handles connection over secure SSE, and you pass the toolset instance directly into your Agent's `toolsets` parameter.

No nuclear documents or reactor reports are saved on Vinkius. The data is processed entirely in memory within ephemeral V8 isolates and delivered directly to your Pydantic AI runtime.

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