How to Use the NIST NVD MCP in Pydantic AI

Guarantee type-safe vulnerability audits in Pydantic AI by validating NIST NVD payloads at runtime.

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 Pydantic AI

Create your Vinkius account to connect NIST NVD 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 NIST NVD with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate NIST NVD payloads with Pydantic AI

The `get_cve_by_id` tool fetches structured vulnerability details that your Pydantic AI agent validates against strict Python types. If the NVD API returns unexpected schemas or missing fields, the framework raises a validation error immediately. This prevents silent data corruption in your security pipelines. Your agent calls `get_cpe_by_id` to fetch product data, knowing the response must conform to your exact Pydantic models before execution continues.

Filter critical threats using type-safe searches

The `search_cve_by_severity` tool restricts vulnerability scans to specific threat levels inside your Pydantic AI agent. The framework enforces strict type constraints on the severity parameters, blocking malformed queries before they reach the network. You configure the agent to run these checks using Streamable HTTP transports. The agent executes `search_cve_by_date` to pull recent threats, parsing the results into clean, typed Python objects for downstream processing.

Audit product dictionaries with Pydantic AI

The `search_cpe_by_keyword` tool queries the official product dictionary to verify your internal software inventory. Your Pydantic AI agent processes the returned CPE records, ensuring every match aligns with your internal configuration schemas. You register the tools by passing `MCPToolset` directly to your agent's `toolsets` parameter. The agent uses `search_cve_by_cwe` to map weaknesses to specific software products without risking runtime type errors.

Setup guide

Set up NIST NVD 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": {
        "nist-nvd-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NIST NVD 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 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 Pydantic AI

Install the slim package with the mcp extra, then instantiate `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset into the `Agent` constructor to expose the vulnerability search tools.

The framework will raise a validation error instantly if a tool like `get_cve_change_history` returns data that violates your defined models. This prevents your agent from processing corrupted or unexpected vulnerability payloads.

Yes, the framework is model-agnostic and lets you run tools like `search_cve_by_cpe` using OpenAI, Gemini, or local models. The type validation occurs at the framework level, independent of the LLM you choose.

No, the older class is deprecated. You must use the unified `MCPToolset` class to connect your agent to the Vinkius-hosted server.

No, the framework operates entirely in your local environment, sending queries directly to the Vinkius endpoint. The Vinkius sandbox executes the NVD queries ephemerally, ensuring your checked CVEs and private software inventories are never persisted.

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