How to Use the NVIDIA AI MCP in CrewAI

Q: Can I limit tool access for specific CrewAI agents using NVIDIA AI?

Yes. Use the toolfilter parameter in your MCP server setup. This allows you to restrict tool exposure to only the agents that require them.

Deploy specialized agent crews using NVIDIA AI and the CrewAI framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA AI MCP to CrewAI

Create your Vinkius account to connect NVIDIA AI 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 NVIDIA AI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent collaboration with CrewAI

Assign `generate_code` to a developer agent and `summarize_text` to a researcher agent within the same crew. They share the same context and collaborate to finish the job. This MCP Server allows your agents to access the NVIDIA API Catalog independently. Each agent in the crew calls the tools it needs to fulfill its role-based mission.

Hierarchical operations in CrewAI

Set up a manager agent to coordinate `text_to_sql` queries across a team of analysts. The manager delegates the heavy lifting to the agents best suited for the task. Use the tool_filter to restrict which agents can access which tools. This keeps your hierarchy clean and ensures that only specific agents perform sensitive operations.

Autonomous monitoring with CrewAI

Deploy a monitor agent that periodically runs `list_models` to check service availability and status. It can alert you if the environment needs attention. Your crew acts without constant manual intervention. By using the NVIDIA AI tools, the agents make decisions based on the latest data retrieved from the API Catalog.

Setup guide

Set up NVIDIA AI 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 NVIDIA AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent NVIDIA AI 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="NVIDIA AI Analyst",
        goal="Access and analyze NVIDIA AI data via MCP.",
        backstory="Expert analyst with direct NVIDIA AI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent NVIDIA AI 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 NVIDIA. 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 NVIDIA AI 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 NVIDIA AI MCP in CrewAI

Add the server URL to the mcps array in your Agent constructor. CrewAI handles the transport layer and tool registration.

Yes. Use the tool_filter parameter in your MCP server setup. This allows you to restrict tool exposure to only the agents that require them.

They do. CrewAI provides a shared memory space for all agents in the crew. The tools write their outputs to this space for other agents to consume.

The framework enforces the sequence you define. Each tool call is awaited, ensuring the output of one agent is available for the next.

We enforce strict isolation between agent sessions. Your data is processed in a transient sandbox; once the inference request to the NVIDIA API Catalog concludes, the memory is cleared.

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