How to Use the NVIDIA API Catalog MCP in LangChain

Q: How do I connect the NVIDIA API Catalog to my LangChain agent?

Install langchain-mcp-adapters and use the MultiServerMCPClient pointing to your Vinkius endpoint. This registers all eight tools on the MCP Server, allowing your agent to call them dynamically.

Q: Can LangChain trace token usage when using the NVIDIA API Catalog?

Yes. When you use nvidiachatcompletion within a LangChain run, you can track performance and latency using LangSmith. You can also query nvidiachecktokenquota directly within a chain to log your remaining credits.

Q: Does the NVIDIA API Catalog support custom fine-tuned models in LangChain?

Yes, it does. Your LangChain agent can call nvidialistloraadapters to check for active fine-tuning overrides. You can then specify these adapter paths when initiating chat completions.

Q: How does the summarization tool work in this setup?

The nvidiasummarizecontent tool processes long text blocks and returns abstract compressions. This is useful for condensing large documents before feeding them into downstream chain steps, saving context window space.

Q: How is my image and prompt data secured when using this MCP Server?

Your chat payloads and raw images sent to nvidiavisioninference pass through an ephemeral, zero-trust V8 sandbox. No data is stored or logged on the proxy; it goes directly to NVIDIA's secure endpoints and vanishes.

Run Nemotron and Llama3 models in your LangChain pipelines with direct token tracking and zero setup overhead.

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 LangChain

Create your Vinkius account to connect NVIDIA API Catalog to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step inference with LangChain chains

Your agent uses `nvidia_chat_completion` to run text completions directly through NVIDIA's optimized infrastructure. By linking this tool with LangChain's conversational chains, you pass variables from previous prompts straight into Nemotron or Llama3 without writing custom API wrappers. You get immediate access to these models without managing local weights or massive hardware setups. This MCP Server lets your agent decide when to trigger a completion based on the current state of your chain.

Monitor model availability and token limits

The `nvidia_check_token_quota` tool gives your LangChain agent real-time visibility into your active credit limits and execution boundaries. This prevents your pipelines from crashing mid-execution due to unexpected rate limits or exhausted balances. Combine this with `nvidia_get_cloud_status` to check the latency of the cloud endpoints before dispatching large batches of requests. This keeps your production workflows predictable and cost-effective.

Run multimodal tasks within LangChain chains

The `nvidia_vision_inference` tool handles graphical and image-based inputs directly inside your LangChain agent runs. You feed images to Llama-Vision models and receive structured diagnostic feedback or textual descriptions instantly. This capability lets you build workflows that process mixed media without jumping between different SDKs. The MCP setup runs through a single endpoint token managed by Vinkius, simplifying your code.

Setup guide

Set up NVIDIA API Catalog MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes NVIDIA API Catalog tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "nvidia-api-catalog-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent NVIDIA API Catalog transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` pointing to your Vinkius endpoint. This registers all eight tools on the MCP Server, allowing your agent to call them dynamically.

Yes. When you use `nvidia_chat_completion` within a LangChain run, you can track performance and latency using LangSmith. You can also query `nvidia_check_token_quota` directly within a chain to log your remaining credits.

Yes, it does. Your LangChain agent can call `nvidia_list_lora_adapters` to check for active fine-tuning overrides. You can then specify these adapter paths when initiating chat completions.

The `nvidia_summarize_content` tool processes long text blocks and returns abstract compressions. This is useful for condensing large documents before feeding them into downstream chain steps, saving context window space.

Your chat payloads and raw images sent to `nvidia_vision_inference` pass through an ephemeral, zero-trust V8 sandbox. No data is stored or logged on the proxy; it goes directly to NVIDIA's secure endpoints and vanishes.

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