How to Use the Nhost MCP in LlamaIndex

Q: How do I make Nhost tools available to my LlamaIndex agent?

Install llama-index-tools-mcp and create a BasicMCPClient with your Vinkius URL. Then, wrap it in an McpToolSpec and call .totoollistasync() to get the tools for your agent.

Q: How does LlamaIndex handle Nhost file uploads and indexing?

Your agent calls the uploadfile tool. LlamaIndex can then take the returned metadata and index it. You can even build a process where it then uses getfile to download the content and index that, too.

Q: Can I restrict which Nhost tools my LlamaIndex agent can use?

Yes. The McpToolSpec has an allowedtools filter. You can provide a list of tool names, like 'getuser', 'getfilepresignedurl', to ensure your agent only has access to specific read-only operations.

Index your Nhost user data and file metadata. Let your LlamaIndex RAG app answer questions based on live API results, not just static docs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nhost MCP to LlamaIndex

Create your Vinkius account to connect Nhost 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 Nhost with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn API Calls into Knowledge

LlamaIndex doesn't just call a tool; it learns from the output. When your agent uses `get_user` to fetch a profile, that user's data can be automatically indexed into a vector store. Now you can ask your RAG application questions like 'What's user_id 123's email?' and get an answer grounded in the actual, most recent API call, not a stale document.

Build a Self-Aware LlamaIndex Agent

Your agent can query its own past actions. After it uses `upload_file`, the file's metadata is indexed. Later, the agent can search for that file's ID or URL without having to call the API again. This creates a memory of its interactions with the Nhost MCP server. It can reason about what files it has access to or what users it has authenticated, making it more efficient and less repetitive.

Grounded Auth and Storage Queries

Combine Nhost tools with your documents. Your agent can first call `get_file_presigned_url` to get a link to a file in Nhost storage, then retrieve the document and index its contents alongside the metadata. This MCP toolset connects the abstract data in your knowledge base to concrete objects in your backend. It's the difference between knowing about a file and being able to actually `get_file` and read it.

Setup guide

Set up Nhost 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 Nhost 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 Nhost tools.",
)
response = await agent.run("List recent Nhost 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 Nhost. 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 Nhost 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 Nhost MCP in LlamaIndex

Install `llama-index-tools-mcp` and create a `BasicMCPClient` with your Vinkius URL. Then, wrap it in an `McpToolSpec` and call `.to_tool_list_async()` to get the tools for your agent.

Yes, that's the core idea. When your agent uses a tool like `get_user`, LlamaIndex can be configured to automatically index the response. This builds a knowledge base of your Nhost users that the agent can query.

Your agent calls the `upload_file` tool. LlamaIndex can then take the returned metadata and index it. You can even build a process where it then uses `get_file` to download the content and index that, too.

Yes. The `McpToolSpec` has an `allowed_tools` filter. You can provide a list of tool names, like `['get_user', 'get_file_presigned_url']`, to ensure your agent only has access to specific read-only operations.

The agent will handle user credentials for auth tools and receive session tokens in return. Because LlamaIndex is designed to index tool outputs, data from `get_user` (like email) or `upload_file` (file metadata) could be stored in your vector database. You must ensure your indexing pipeline and vector store are secure.

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