How to Use the Ninox MCP in LlamaIndex

Q: Can my LlamaIndex agent write data back to Ninox?

Yes. Your agent can run createrecords or updaterecord to modify your tables. This lets you build active agents that do more than just read static information.

Q: How does LlamaIndex handle complex queries on Ninox tables?

The agent can use executeninoxscript to run native database queries. LlamaIndex then indexes the resulting dataset, making complex relational data searchable via semantic queries.

Build a searchable knowledge base from your relational tables by indexing Ninox data with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ninox MCP to LlamaIndex

Create your Vinkius account to connect Ninox 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 Ninox with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index schemas into LlamaIndex vector stores

The `get_database_schema` tool exposes your schema, allowing the MCP Server to deliver structured metadata to LlamaIndex. This allows the agent to build a semantic index of your database layout, making schema discovery highly accurate. Instead of guessing table structures, your agent queries this vector index. It learns exactly where to find records before calling tools like `list_records` to pull the actual data.

Ground RAG applications in live Ninox records

The `list_records` tool extracts raw data directly from your tables to ground your agent's answers in real-time facts. LlamaIndex indexes these records on the fly, eliminating LLM hallucinations. If a user asks about an order status, the agent pulls the record using `get_record`. It inserts the retrieved fields straight into the response context, keeping your customer support responses completely accurate.

Update your database via LlamaIndex MCP Server actions

The `update_record` tool writes structural changes and updates directly back to your Ninox tables based on agent decisions. This turns your static knowledge retriever into an active read-write pipeline. When the agent identifies discrepancies in your vector index, it uses `create_records` to resolve them. You get a self-correcting database that stays in sync with your business documents.

Setup guide

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

Install the MCP tool package and initialize the client using your Vinkius server URL. Use `McpToolSpec` to convert the tools into LlamaIndex-compatible functions, then pass them to your agent.

Yes. Your agent can run `create_records` or `update_record` to modify your tables. This lets you build active agents that do more than just read static information.

The agent can use `execute_ninox_script` to run native database queries. LlamaIndex then indexes the resulting dataset, making complex relational data searchable via semantic queries.

Yes. You can configure the allowed tools list during setup. This prevents the agent from calling tools like `delete_record` on critical tables while keeping read tools active.

Your workspace schemas and records are retrieved through a secure V8 sandbox. Vinkius handles the credentials, so your raw database tokens are never exposed to the client or stored in the index.

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