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

Q: How do I add the NLM RxNorm (Drug Database) to my Google ADK setup?

Install google-adk, initialize an McpToolset with StreamableHttpServerParameters, and pass it to your LlmAgent under the tools parameter.

Q: Can I limit which NLM RxNorm (Drug Database) tools the Google ADK agent sees?

Yes. If you only need NDC lookups, pass a toolnames list to the McpToolset. The agent will ignore the class and property tools entirely.

Give your Google ADK agents direct access to federal drug terminologies, NDCs, and RxCUIs for enterprise healthcare data pipelines.

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 Google ADK

Create your Vinkius account to connect NLM RxNorm (Drug Database) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map BigQuery records with this MCP Server

You likely have millions of unstandardized medication records sitting in BigQuery. By connecting this MCP Server, your Gemini agent iterates through those rows and maps raw text to standardized federal codes. The agent uses `get_all_properties` and `get_rx_concept_properties` to pull the exact semantic relationships for each drug. It then writes the normalized RxCUIs back into your BigQuery tables, creating a clean dataset for downstream Vertex AI models.

Long-context clinical analysis

Gemini's massive context window changes how you handle clinical documentation. You can feed an entire medical history into the Google ADK and have the agent extract every mentioned medication. The agent then fires `get_all_related_info` and `get_related_by_type` against the database for every extracted drug. Because Gemini holds over a million tokens, it easily absorbs the massive JSON responses from these queries without losing track of the patient's timeline.

Spelling and term normalization

Clinical notes are full of typos. When a doctor misspells a generic name, your agent catches the error and runs `get_spelling_suggestions` to find the closest match in the RxNorm vocabulary. Once the agent confirms the correct spelling, it calls `get_rxterm_display_name` to grab the consumer-friendly label. You restrict the exposed tools using the `tool_names` filter in your `McpToolset` so the agent only focuses on terminology matching.

Setup guide

Set up NLM RxNorm (Drug Database) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with NLM RxNorm (Drug Database) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="NLM RxNorm (Drug Database)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to NLM RxNorm (Drug Database) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install `google-adk`, initialize an `McpToolset` with `StreamableHttpServerParameters`, and pass it to your `LlmAgent` under the `tools` parameter.

Yes. If you only need NDC lookups, pass a `tool_names` list to the `McpToolset`. The agent will ignore the class and property tools entirely.

Gemini agents execute tool calls rapidly. You should implement a delay in your agent loop or use an external caching layer to avoid hitting the NIH REST API limits.

Yes. As long as your Gemini model supports tool calling, the agent routes queries to the MCP server and parses the RxNorm responses automatically.

This server processes medication strings and identifiers like NDCs. It operates inside a secure V8 Isolate Sandbox. Keep patient names and dates of birth out of the prompts, and the database will only ever see raw pharmaceutical search terms.

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