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

Q: How do I pass the NRC ADAMS (Nuclear Regulatory) tools to a LangChain agent?

Install langchain-mcp-adapters and use the MultiServerMCPClient to connect to the NRC ADAMS MCP Server. Call client.gettools() to retrieve the getnrcrssfeed and searchadamslegacy tools, then pass them directly into your LangChain createagent call.

Run multi-step regulatory research chains across real-time reactor feeds and legacy NRC ADAMS documents with LangChain.

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 LangChain

Create your Vinkius account to connect NRC ADAMS (Nuclear Regulatory) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain real-time reactor alerts with LangChain agents

Your LangChain agent can monitor live nuclear plant operations by fetching data through `get_nrc_rss_feed`. The output feeds directly into your next LangChain link, letting you parse raw safety events without manual copy-pasting. This setup lets you build autonomous LangChain pipelines that watch for reactor anomalies. When an event triggers, LangChain routes the NRC status details to your summary models or notification channels instantly.

Trace legacy document queries using LangSmith

Querying the legacy WBA API via `search_adams_legacy` requires precise filtering parameters that you can construct within a LangChain run. By wrapping this NRC tool in a LangChain sequence, you can debug complex query structures inside LangSmith to see exactly why a search succeeded or failed. This visibility ensures you don't waste LangChain tokens on bad legacy ADAMS queries. You trace the exact parameters sent to the retiring database, verifying your LangChain agent constructs the complex filter arguments correctly.

Multi-server coordination for nuclear compliance

Combine the `get_nrc_rss_feed` and `search_adams_legacy` tools with other APIs in a single LangChain MultiServerMCPClient setup. Your LangChain agent can pull a reactor incident report from the NRC database and immediately check it against internal compliance checklists or vector stores. This approach removes the boundary between public regulatory records and your private LangChain data. You build unified LangChain workflows where the agent decides when to query the legacy ADAMS archive and when to pull live RSS updates.

Setup guide

Set up NRC ADAMS (Nuclear Regulatory) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes NRC ADAMS (Nuclear Regulatory) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "nrc-adams-nuclear-regulatory-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent NRC ADAMS (Nuclear Regulatory) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` to connect to the NRC ADAMS MCP Server. Call `client.get_tools()` to retrieve the `get_nrc_rss_feed` and `search_adams_legacy` tools, then pass them directly into your LangChain `create_agent` call.

Your LangChain agent uses its reasoning loop to construct the nested `q` parameter required by `search_adams_legacy`. You can use LangSmith to monitor the exact JSON payload sent to the retiring WBA API via MCP during execution.

Yes, you can use LangGraph or a persistent LangChain session to maintain context across multiple NRC ADAMS runs. This lets your LangChain agent compare new entries from `get_nrc_rss_feed` against previously analyzed events to flag recurring reactor issues.

You will need to update the tool references in your LangChain chains before the June 2026 retirement date. The `search_adams_legacy` tool will stop functioning, but you can continue using `get_nrc_rss_feed` for real-time LangChain status updates.

No, the server handles only public NRC documents and public RSS feeds. Your LangChain connection runs inside an isolated sandbox, meaning query parameters and retrieved reactor texts never exit your local infrastructure or your chosen LLM provider's secure boundary.

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