How to Use the NIST NVD MCP in OpenAI Agents SDK

Q: How do I configure the NIST NVD MCP Server with the OpenAI Agents SDK?

Install the package with pip and initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this server object into your Agent constructor using the mcpservers parameter to auto-discover all security tools.

Q: Can I trace NVD searches in the developer dashboard?

Yes, every call to searchcvebydate appears in your OpenAI developer dashboard. You see the exact query parameters, the raw JSON payload returned, and how your agent interpreted the vulnerability.

Run OpenAI Agents SDK with real-time vulnerability data to automatically block insecure deployments before they hit production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NIST NVD MCP to OpenAI Agents SDK

Create your Vinkius account to connect NIST NVD 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 NIST NVD with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scan software packages with OpenAI Agents SDK

The `search_cve_by_cpe` tool lets your OpenAI Agents SDK agent scan software packages for active vulnerabilities. Your agent inspects your package manifests, queries the NVD database, and flags matches instantly. By feeding this data directly into the SDK's built-in guardrails, you can stop insecure builds programmatically. The agent runs these checks asynchronously using `MCPServerStreamableHttp` to ensure your deployment pipeline never blocks on slow API responses.

Verify CVE histories inside your safety guardrails

The `get_cve_change_history` tool pulls the modification logs of specific vulnerabilities directly into your OpenAI Agents SDK workflow. This stops your security agents from acting on stale or disputed vulnerability data during automated audits. You configure the agent with safety rules that trigger whenever a CVE record changes. The SDK's tracing dashboard records every lookup, giving you a clear audit trail of how your agent assessed the threat.

Route severe threats to specialized security agents

The `search_cve_by_severity` tool filters the vulnerability feed so your OpenAI Agents SDK setup only alerts on critical issues. High-severity threats bypass standard triage and go straight to your senior response agent. This setup uses agent handoffs to transition from general monitoring to active incident response. Your primary agent detects the CVE, runs `get_cve_by_id` to gather details, and passes the payload to a specialized patching agent.

Setup guide

Set up NIST NVD 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 NIST NVD tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package with pip and initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this server object into your Agent constructor using the `mcp_servers` parameter to auto-discover all security tools.

The SDK manages connection pools through its async context manager when calling tools like `search_cve_by_keyword`. Setting `cacheToolsList=True` prevents redundant API calls and protects your NVD rate limits.

You write custom guardrails in python that inspect the output of `get_cve_by_id` before the agent proceeds. The SDK intercepts the tool output, runs your validation logic, and halts execution if a critical vulnerability threshold is crossed.

Yes, every call to `search_cve_by_date` appears in your OpenAI developer dashboard. You see the exact query parameters, the raw JSON payload returned, and how your agent interpreted the vulnerability.

The MCP server only sends the specific CPE strings to the NIST NVD API during `list_cpe_matches` lookups. Vinkius runs this server in a zero-trust, ephemeral V8 sandbox, meaning your raw codebase and private package manifests are never stored or logged.

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