How to Use the NHTSA Vehicle Safety MCP in OpenAI Agents SDK

Q: How do I connect the NHTSA Vehicle Safety server to my OpenAI Agents SDK project?

Just pass the Vinkius URL to the MCPServerStreamableHttp constructor. Your agent auto-discovers all 13 tools, so there's no manual mapping. Set cacheToolsList=True to speed up subsequent interactions.

Q: Can my OpenAI Agents SDK agent search NHTSA Vehicle Safety recalls for a whole model year?

Yes. The getrecallsbyvehicle tool can take just a year. Your agent can pull all recalls for that year and then filter or summarize the results for you.

Q: What's the best way to check a specific vehicle?

The most direct way is to use the decodevin tool with the vehicle's 17-digit VIN. This gives you the exact specs, which you can then use with getrecallsbyvehicle for a precise search.

Build production safety agents with the OpenAI Agents SDK that check vehicle recalls and complaints automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NHTSA Vehicle Safety MCP to OpenAI Agents SDK

Create your Vinkius account to connect NHTSA Vehicle Safety 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 NHTSA Vehicle Safety with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Automated Fleet Audits

Point your agent at a list of VINs. It'll use `decode_vin` to confirm the vehicle specs, then run each one through `get_recalls_by_vehicle` and `get_complaints_by_vehicle`. You get a complete safety profile for every car in your fleet without lifting a finger. The OpenAI dashboard gives you a full trace of every tool call. You can see exactly what data the agent checked and when. This isn't a black box; it's an auditable compliance system built for production.

Research a Vehicle Before You Buy

Tell your agent the make, model, and year of a car you're considering. It can pull the official crash test results with `get_safety_ratings` and dig up owner-filed issues using `get_complaints_by_vehicle`. No more wading through forums and biased reviews. You can even set up specialized agents. One agent could gather the raw data, and a second could summarize the findings. OpenAI's framework handles the handoff, so you just get a clean, simple answer.

Find Local Car Seat Checks with your OpenAI Agents SDK

Getting a car seat installed correctly is serious business. Have your agent use `get_car_seat_stations_by_zip` with your zip code. It returns a list of certified inspection stations nearby, including their hours and phone numbers. This is where guardrails are key. Your agent isn't just searching the web; it's hitting an official government database. The OpenAI Agents SDK helps ensure the agent sticks to trusted tools like this MCP server for critical safety information.

Setup guide

Set up NHTSA Vehicle Safety 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 NHTSA Vehicle Safety tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives NHTSA Vehicle Safety tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NHTSA Vehicle Safety 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="NHTSA Vehicle Safety Agent",
            instructions="You have access to NHTSA Vehicle Safety 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 NHTSA. 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 NHTSA Vehicle Safety 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 NHTSA Vehicle Safety MCP in OpenAI Agents SDK

Just pass the Vinkius URL to the `MCPServerStreamableHttp` constructor. Your agent auto-discovers all 13 tools, so there's no manual mapping. Set `cacheToolsList=True` to speed up subsequent interactions.

Yes. The `get_recalls_by_vehicle` tool can take just a year. Your agent can pull all recalls for that year and then filter or summarize the results for you.

This MCP server connects directly to the official NHTSA v2 API. The data is as current as what the government publishes. There's no intermediate caching layer to fall out of sync.

The most direct way is to use the `decode_vin` tool with the vehicle's 17-digit VIN. This gives you the exact specs, which you can then use with `get_recalls_by_vehicle` for a precise search.

Your agent sends the VIN to the Vinkius-managed server, which passes it to the NHTSA API. The entire process happens in an ephemeral, zero-trust sandbox. Vinkius doesn't log or store the VINs you process.

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