How to Use the NVIDIA API Catalog MCP in CrewAI

Q: How do I filter tools for NVIDIA API Catalog in a CrewAI crew?

Use the toolfilter parameter in your MCP server configuration. This limits which agents have access to specific tools, keeping your operation focused and secure.

Q: How do I scale my CrewAI operations with this server?

Monitor your token limits via nvidiachecktokenquota. If you hit your limit, your agents can automatically trigger a cleanup or stop less important background tasks.

Q: Are there latency concerns for large crews?

Use nvidiagetcloudstatus to track latency. If your crew grows to include dozens of agents, you can adjust your concurrency settings based on the feedback from the server.

Deploy autonomous agent crews with NVIDIA API Catalog to handle research, analysis, and execution without human oversight.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA API Catalog MCP to CrewAI

Create your Vinkius account to connect NVIDIA API Catalog 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 API Catalog with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate specialized agent roles

Assign research and analysis to different crew members using the model catalog. Your monitor agent calls `nvidia_list_foundation_models` to assign the right model to the right specialist. This ensures your agents aren't just guessing. They use specific models tuned for their assigned roles, making your multi-agent team more efficient and accurate.

Autonomous data analysis crews

Let your agents perform deep analysis on massive data sets. You use `nvidia_vision_inference` for graphical diagnostics and `nvidia_summarize_content` to boil down the findings. Your crew works in the background to identify trends. Once they finish, they can push the final summary to your dashboard, saving you hours of manual review.

Check cloud health autonomously

Keep your agents informed about the status of their infrastructure. Your moderator agent calls `nvidia_get_cloud_status` to ensure the inference endpoints are ready for heavy lifting. If the service is down, the moderator reassigns tasks to other crew members or pauses the operation. This keeps your pipeline moving even when cloud conditions shift.

Setup guide

Set up NVIDIA API Catalog 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 API Catalog tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Use the `tool_filter` parameter in your MCP server configuration. This limits which agents have access to specific tools, keeping your operation focused and secure.

CrewAI agents share memory across the session. You can store the output of `nvidia_generate_embeddings` in this memory to give every agent context on past research.

It does. Because the tools are stateless and accessible via a shared endpoint, multiple agents can call them concurrently without interfering with each other's work.

Monitor your token limits via `nvidia_check_token_quota`. If you hit your limit, your agents can automatically trigger a cleanup or stop less important background tasks.

Use `nvidia_get_cloud_status` to track latency. If your crew grows to include dozens of agents, you can adjust your concurrency settings based on the feedback from the server.

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