How to Use the ncScale MCP in LlamaIndex

Q: How do I add the ncScale MCP Server to LlamaIndex?

Install llama-index-tools-mcp. Set up a BasicMCPClient pointing to your Vinkius endpoint. Convert the endpoints using McpToolSpec and pass them to your FunctionAgent.

Q: Can LlamaIndex query historical ncScale tickets?

It handles this perfectly. You run listtickets to pull past issues and embed the text. Your agent can then answer questions about recurring bugs based on past resolutions.

Index your no-code stack. LlamaIndex turns ncScale logs and alerts into a searchable knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ncScale MCP to LlamaIndex

Create your Vinkius account to connect ncScale 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 ncScale with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a LlamaIndex RAG Pipeline for Logs

The `list_logs` tool from this MCP Server provides raw system data that LlamaIndex embeds directly into a vector store. You stop grepping through text files and start querying your infrastructure semantically. Ask your agent why the payment webhook failed last Tuesday. It searches the index, retrieves the exact log entries, and synthesizes an answer. The context is grounded in actual historical data rather than LLM guesswork.

Index Dashboards and Alerts

Your agent calls `list_alerts` and `list_dashboards` to pull current system health metrics into a unified index. It stores these active monitoring states as queryable nodes. When a new incident occurs, the agent compares the current alert against indexed historical alerts. It immediately identifies if this exact failure pattern happened before. You get instant context on how the previous team fixed it using the MCP Server data.

Semantic Search for No-Code Nodes

Let LlamaIndex map your architecture by pulling data via `list_nodes` and `list_integrations`. Documenting custom Bubble or Make scenarios is tedious, but this automates the mapping of relationships between your tools. You can then ask the agent which nodes depend on a specific Airtable base. It uses `get_node` to pull the configurations and cross-references them against your index. You get a precise dependency graph before you break anything.

Setup guide

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

Install `llama-index-tools-mcp`. Set up a `BasicMCPClient` pointing to your Vinkius endpoint. Convert the endpoints using `McpToolSpec` and pass them to your `FunctionAgent`.

It handles this perfectly. You run `list_tickets` to pull past issues and embed the text. Your agent can then answer questions about recurring bugs based on past resolutions.

That depends on your log volume. Most teams schedule a job to pull `list_logs` every few minutes, updating the vector store dynamically so the agent always searches fresh data.

Yes. You can restrict the agent to read-only observability. Just use the `allowed_tools` parameter to expose `get_alert` while hiding broader workspace queries.

The server processes sensitive operational data including error payloads, node configurations, and user IDs. Vinkius secures this transit via ephemeral sandboxes. The embeddings and vector storage happen locally on your machine or within your private cloud environment.

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