How to Use the NLM RxNorm (Drug Database) MCP in LangChain

Q: How do I initialize the NLM RxNorm (Drug Database) MCP Server in LangChain?

Install langchain-mcp-adapters. Use MultiServerMCPClient pointing to the server URL, then call client.gettools() to pass the 21 drug tools to your agent.

Q: Can LangChain agents chain NLM RxNorm (Drug Database) tools together?

Yes. An agent calls findrxcuibystring to get an ID, then immediately passes that ID into getallrelatedinfo to find brand names and ingredients.

Q: Does the NLM RxNorm (Drug Database) work with LangSmith tracing in LangChain?

It does. Every call to getndcproperties or getrxconceptproperties appears in your trace. You see the exact latency and the raw JSON returned by the NIH.

Q: What happens if the drug name is misspelled?

The agent uses getspellingsuggestions or getapproximatematch to find the correct term before re-attempting the primary search.

Build multi-step clinical reasoning chains in LangChain that map messy drug strings directly to standardized RxCUIs and NDCs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NLM RxNorm (Drug Database) MCP to LangChain

Create your Vinkius account to connect NLM RxNorm (Drug Database) 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 NLM RxNorm (Drug Database) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map drug names to NDCs in LangChain

Start your LangChain agent with `find_rxcui_by_string`. The agent takes raw text from a clinical note, runs it through the tool, and extracts the standardized identifier. Pass that RxCUI directly into `get_ndcs` or `get_all_properties` in the next chain link. The framework handles the state transfer automatically, letting you build a medication reconciliation pipeline without writing manual data transforms.

Fix clinical spelling errors automatically

`get_spelling_suggestions` acts as the first line of defense when your agent hits a failed lookup. Doctors misspell drug names constantly in raw text. Your ReAct agent catches the null response from a failed search, triggers the spelling tool, and re-runs the query with the corrected string. LangSmith logs the exact sequence so you can track how often the agent corrects human input.

Query drug classes via this MCP Server

`get_class_by_rxnorm_drug_id` lets your agent group medications into clinical categories like ATC or VA classes. You pass the drug ID, and the MCP server returns the hierarchy. If you need the inverse operation, `get_class_members` pulls every drug belonging to that class. You feed this list into a vector store or use it to filter downstream API calls in your chain.

Setup guide

Set up NLM RxNorm (Drug Database) 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 NLM RxNorm (Drug Database) 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({
    "nlm-rxnorm-drug-database-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 NLM RxNorm (Drug Database) 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 NLM RxNorm. 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 NLM RxNorm (Drug Database) 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 NLM RxNorm (Drug Database) MCP in LangChain

Install `langchain-mcp-adapters`. Use `MultiServerMCPClient` pointing to the server URL, then call `client.get_tools()` to pass the 21 drug tools to your agent.

Yes. An agent calls `find_rxcui_by_string` to get an ID, then immediately passes that ID into `get_all_related_info` to find brand names and ingredients.

It does. Every call to `get_ndc_properties` or `get_rx_concept_properties` appears in your trace. You see the exact latency and the raw JSON returned by the NIH.

The agent uses `get_spelling_suggestions` or `get_approximate_match` to find the correct term before re-attempting the primary search.

This server processes raw drug strings, RxCUIs, and NDCs. It does not touch patient health information (PHI). Your agent only sends the medication names to the NIH endpoints.

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