How to Use the NVIDIA AI MCP in LlamaIndex

Q: How do I install the NVIDIA AI MCP Server tools in LlamaIndex?

Run pip install llama-index-tools-mcp in your terminal. Initialize the BasicMCPClient with your Vinkius URL, wrap it in a McpToolSpec, and call totoollistasync() to get the tool list for your agent.

Q: Can I filter which NVIDIA AI tools are exposed to LlamaIndex?

Yes. Use the allowedtools filter when configuring your McpToolSpec to expose only specific tools like getembeddings or chatcompletion to your LlamaIndex agent, preventing unauthorized tool execution.

Q: How does LlamaIndex handle embeddings generated by NVIDIA AI?

Your LlamaIndex pipeline calls getembeddings to generate vectors for your text nodes. These vectors are then stored in your chosen vector database, ensuring search queries match your indexed documents.

Q: Does this MCP Server support the LlamaIndex resource protocol?

Yes. Set includeresources=True when initializing the client to let your LlamaIndex agent read resources exposed by the server alongside the standard tools.

Index live outputs from NVIDIA AI models directly into your LlamaIndex vector stores using this MCP Server.

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 LlamaIndex

Create your Vinkius account to connect NVIDIA AI to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live model outputs into LlamaIndex RAG pipelines

The `get_embeddings` tool generates vector representations of your documents using the `nvidia/nv-embed-v1` model. LlamaIndex takes these vectors and writes them directly to your index, bypassing manual vectorization scripts. When a query comes in, your pipeline uses `ask_question` to query the 405B parameter model with the retrieved context. This MCP Server ensures your index always has access to high-performance embeddings and reasoning models.

Build queryable knowledge bases from live API tools

The `summarize_text` tool processes long documents and outputs concise summaries that LlamaIndex indexes for quick semantic search. You avoid indexing raw, noisy text by running this step first. If your data is in multiple languages, the `translate_text` tool standardizes the documents before indexing. This LlamaIndex integration lets you build a unified, searchable knowledge base from messy, multi-lingual sources.

Turn database schemas into searchable indexes

The `text_to_sql` tool converts natural language queries into SQL, which LlamaIndex runs to fetch raw data. You then index this tabular data or feed it into `chat_completion` to generate natural language answers. Your agent uses `list_models` to find the best model for the current query complexity. This MCP Server gives your LlamaIndex pipeline direct access to structured data sources and advanced reasoning.

Setup guide

Set up NVIDIA AI MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all NVIDIA AI MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to NVIDIA AI tools.",
)
response = await agent.run("List recent NVIDIA AI data")

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 LlamaIndex

Run `pip install llama-index-tools-mcp` in your terminal. Initialize the `BasicMCPClient` with your Vinkius URL, wrap it in a `McpToolSpec`, and call `to_tool_list_async()` to get the tool list for your agent.

Yes. Use the `allowed_tools` filter when configuring your `McpToolSpec` to expose only specific tools like `get_embeddings` or `chat_completion` to your LlamaIndex agent, preventing unauthorized tool execution.

Your LlamaIndex pipeline calls `get_embeddings` to generate vectors for your text nodes. These vectors are then stored in your chosen vector database, ensuring search queries match your indexed documents.

Yes. Set `include_resources=True` when initializing the client to let your LlamaIndex agent read resources exposed by the server alongside the standard tools.

Your SQL queries, text inputs, and database schemas are sent directly to the NVIDIA API Catalog via a secure, token-authorized V8 sandbox. Vinkius destroys the container immediately after the run, ensuring no data persists.

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