How to Use the NLM RxNorm (Drug Database) MCP in OpenAI Agents SDK

Q: How do I install the NLM RxNorm (Drug Database) for the OpenAI Agents SDK?

Run pip install openai-agents. Create an MCPServerStreamableHttp instance with your Vinkius URL and pass it to the mcpservers array in your Agent constructor.

Q: Can the OpenAI Agents SDK cache the NLM RxNorm (Drug Database) tools?

Yes. You should set cacheToolsList=True when configuring the MCP connection. This prevents the agent from re-fetching all 21 drug mapping tools on every single turn.

Connect the NLM RxNorm database to your OpenAI Agents SDK to safely map drug names, NDCs, and clinical properties in production.

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 OpenAI Agents SDK

Create your Vinkius account to connect NLM RxNorm (Drug Database) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Drug mapping with OpenAI Agents SDK guardrails

Your OpenAI agent needs to resolve a misspelled trade name to a standard RxCUI before executing a clinical workflow. By connecting this MCP Server, the agent automatically discovers `find_rxcui_by_string` and `get_approximate_match` to handle the normalization step. Because the framework enforces strict guardrails, you can require the agent to verify the RxCUI exists before moving to the next step. If a mapping fails, the agent hands off the task to a specialized error-handling routine instead of hallucinating a drug code.

Exact package code retrieval

When processing pharmacy claims, you need exact National Drug Codes. Your agent calls `get_ndcs` using the verified RxCUI to pull the active package identifiers directly from the federal database. You then use `get_ndc_properties` to verify packaging and manufacturer details. The SDK's built-in tracing lets you watch the exact inputs and outputs of these API calls in the OpenAI dashboard, making debugging straightforward when a claim rejects.

Clinical class cross-referencing

Building an agent to review medication lists requires understanding drug classes. The system triggers `get_class_by_rxnorm_drug_id` to find where a specific medication sits in the ATC or VA classification hierarchy. From there, it runs `find_similar_classes_by_drug_list` to check if a patient takes multiple drugs with overlapping therapeutic effects. You cache the tools list using `cacheToolsList=True` to keep these multi-step reasoning loops fast and cheap.

Setup guide

Set up NLM RxNorm (Drug Database) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all NLM RxNorm (Drug Database) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives NLM RxNorm (Drug Database) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NLM RxNorm (Drug Database) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="NLM RxNorm (Drug Database) Agent",
            instructions="You have access to NLM RxNorm (Drug Database) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Run `pip install openai-agents`. Create an `MCPServerStreamableHttp` instance with your Vinkius URL and pass it to the `mcp_servers` array in your Agent constructor.

Yes. You should set `cacheToolsList=True` when configuring the MCP connection. This prevents the agent from re-fetching all 21 drug mapping tools on every single turn.

Your agent reads the status payload. You can write a guardrail instructing the agent to stop and request human review whenever a retired drug concept is detected.

Absolutely. You can dedicate one agent to handle RxNorm lookups and have your main clinical agent hand off queries when it needs an NDC or RxCUI verification.

No. The server only receives drug names, RxCUIs, and NDCs. You must strip all Protected Health Information before your agent sends a query to `find_rxcui_by_string`. The transport layer relies on an ephemeral, zero-trust sandbox.

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