How to Use the NIST NVD MCP in CrewAI

Q: How can a CrewAI team collaborate on a single vulnerability from the NIST NVD?

An agent can find a CVE with searchcvebykeyword and pass the CVE ID to another agent in the crew. That second agent can then use getcvebyid to get the details, sharing the context to inform its own tasks.

Deploy an autonomous security team with CrewAI agents that research, analyze, and act on NIST NVD vulnerability data.

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 CrewAI

Create your Vinkius account to connect NIST NVD to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Vulnerability Research Crew

Assign roles to your agents for a complete security pipeline. A 'Scout' agent can use `search_cve_by_date` and `search_cve_by_keyword` to constantly scan the horizon for new threats in the NIST NVD. It finds potential issues and passes them to the next agent. A second 'Analyst' agent takes the CVE IDs from the Scout. It uses `get_cve_by_id` to pull full details and `search_cve_by_cwe` to understand the weakness class. This specialization makes your crew efficient and focused.

Automate Impact Analysis

An 'Impact-Assessor' agent can determine what your organization is exposed to. This agent maintains a list of your software stack's CPEs. It uses `search_cve_by_cpe` to cross-reference new vulnerabilities against your known products. When a match is found, it has everything it needs: the CVE details from the Analyst and the affected internal system. It then passes a concise, actionable report to a 'Responder' agent, all without human intervention. This is how you scale security operations with an MCP Server.

Build an Autonomous Response Team

The final step is action. A 'Responder' agent receives the high-priority, validated threats. Based on the severity from `get_cve_by_id`, it can decide to open a high-priority ticket, add an item to a firewall blocklist, or alert the security team. Your CrewAI team works together, sharing context through each step. The Scout finds it, the Analyst vets it, the Assessor checks for internal impact, and the Responder acts. It's a full security workflow, running autonomously.

Setup guide

Set up NIST NVD MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke NIST NVD tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="NIST NVD Analyst",
    goal="Access and analyze NIST NVD data via MCP.",
    backstory="Expert analyst with direct NIST NVD access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent NIST NVD transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="NIST NVD Analyst",
        goal="Access and analyze NIST NVD data via MCP.",
        backstory="Expert analyst with direct NIST NVD access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent NIST NVD transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

An agent can find a CVE with `search_cve_by_keyword` and pass the CVE ID to another agent in the crew. That second agent can then use `get_cve_by_id` to get the details, sharing the context to inform its own tasks.

Yes, this is exactly what CrewAI is designed for. Set up a sequential crew where the first agent uses `search_cve_by_date` and passes any critical findings from the NIST NVD to a second agent for action.

When defining your agent in CrewAI, you can pass a curated list of tools from this MCP. For example, give your 'Scout' agent only the `search_*` tools, and your 'Analyst' agent only the `get_*` tools from the NIST NVD server.

Definitely. An 'Auditor' agent could be tasked with using the `get_cve_change_history` tool. It can monitor for changes to high-profile CVEs and report on any modifications to the official record.

Your agents only exchange public data with the server, like CVE identifiers (e.g., 'CVE-2023-1234') and CPE product strings. The server doesn't require access to your internal systems or sensitive information. Each transaction is isolated and secure.

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