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

Q: How do I configure the NLM RxNorm (Drug Database) in Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset with your Vinkius URL and pass it to the toolsets array when initializing your Agent.

Q: Should I use MCPServerHTTP for this integration?

No. That class is deprecated. You must use the unified MCPToolset approach to connect the MCP server to your agent.

Connect the federal drug database to Pydantic AI and enforce strict type validation on every RxCUI, NDC, and medication property.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe NDC retrieval via MCP Server

Healthcare applications cannot tolerate hallucinated drug codes. By linking this MCP Server to Pydantic AI, you force the language model to pull real NDCs using `get_ndcs` instead of guessing. When the agent checks a code with `get_ndc_status`, Pydantic AI validates the response payload against your defined schemas at runtime. If the NLM API returns an unexpected format, the framework fails loudly with a validation error, preventing corrupt data from entering your database.

Validated class hierarchies

Building a model-agnostic clinical rules engine requires reliable drug classifications. Your agent uses `get_class_by_rxnorm_drug_id` to identify the VA class for a specific RxCUI. It then executes `get_drugs` to find related products. Because Pydantic AI handles the tool execution, you can swap between OpenAI and Anthropic models without rewriting your parsing logic. The validation layer guarantees the output structure remains identical regardless of the underlying LLM.

Strict relationship mapping

Navigating the complex web of drug ingredients and brand names demands precision. You instruct the agent to use `get_related_by_relationship` to find the exact trade names for a generic ingredient. The agent then triggers `find_related_ndcs` to get the package codes for those specific brands. Pydantic AI ensures every step of this multi-tool chain adheres to your strict typing requirements, stopping the agent immediately if a step returns missing fields.

Setup guide

Set up NLM RxNorm (Drug Database) 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": {
        "nlm-rxnorm-drug-database-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NLM RxNorm (Drug Database) tools.",
)

result = await agent.run("List recent NLM RxNorm (Drug Database) 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 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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` with your Vinkius URL and pass it to the `toolsets` array when initializing your Agent.

Yes. The framework enforces strict type checking on every response. If a drug query returns an unexpected JSON structure, Pydantic AI throws a validation error immediately.

Any model supported by the framework. You can use Gemini, Claude, or local models, and the tool execution will function identically across all of them.

No. That class is deprecated. You must use the unified `MCPToolset` approach to connect the MCP server to your agent.

The server runs in an ephemeral zero-trust environment. It only processes the specific medication names or RxCUIs your agent sends. Strip all clinical notes of identifying patient details before passing them to the toolset.

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