How to Use the NVIDIA NIM MCP in CrewAI

Q: How do I filter NVIDIA NIM tools for CrewAI agents?

You can use the toolfilter option in your MCP configuration to expose only the necessary functions like nimgetmetrics to specific agents in the crew.

Q: Can CrewAI agents read NVIDIA NIM container logs?

Yes, provide nimgetcontainerlogs to your research agent. It can analyze the logs to find the root cause of any inference failures.

Q: How do I list active models in CrewAI using NVIDIA NIM?

Give your moderator agent the nimlistmodels tool. It will track which models are available and assign tasks to the correct inference target.

Deploy autonomous agent crews with CrewAI to monitor and manage your NVIDIA NIM infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA NIM MCP to CrewAI

Create your Vinkius account to connect NVIDIA NIM 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 NIM with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous GPU monitoring agents

Task a specialized agent with running `nim_get_gpu_status` at set intervals to watch for hardware memory bottlenecks. The agent can report back or trigger corrective actions if limits are exceeded. This removes the need for human oversight of your hardware. Your crew handles the observation and status reporting in the background.

Automated inference scaling crews

Set up an agent to analyze `nim_get_metrics` and use `nim_scale_replicas` to keep your inference performance within SLA targets. The agent acts as the infrastructure lead for your deployment. Your deployment adjusts itself to traffic without manual intervention. It's a closed-loop system where the agents own the hardware lifecycle.

System-wide health verification

Use `nim_check_health_live` and `nim_check_health_ready` as core tools for your moderator agent. It checks the entire stack to ensure the NVIDIA NIM server is stable. This ensures your crew only works on healthy infrastructure. If a component stops responding, the agent knows immediately and can escalate the issue.

Setup guide

Set up NVIDIA NIM 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 NIM tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can use the tool_filter option in your MCP configuration to expose only the necessary functions like `nim_get_metrics` to specific agents in the crew.

Yes, provide `nim_get_container_logs` to your research agent. It can analyze the logs to find the root cause of any inference failures.

It is built for this. You can share the server connection across your entire crew so every agent has access to real-time hardware data.

Give your moderator agent the `nim_list_models` tool. It will track which models are available and assign tasks to the correct inference target.

Your GPU status and performance data are accessed via secure local transport. The information is strictly isolated to your agent sessions and never leaves your control.

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