How to Use the AirOps MCP in LlamaIndex

Q: How does LlamaIndex handle document uploads to AirOps?

Your agent uses the uploadfile tool to send local documents directly to the remote server. Once uploaded, these files are processed and indexed, making them immediately available for workflow runs or memory searches.

Q: How are my uploaded files and memory queries secured?

Every file uploaded via uploadfile is encrypted at rest using AES-256 encryption. Vinkius processes all tool calls within ephemeral V8 isolates that destroy all temporary data immediately after execution. Your search queries and document contents are never exposed to external networks.

Index live AirOps workflow outputs and memory documents into LlamaIndex using this high-performance 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 AirOps MCP to LlamaIndex

Create your Vinkius account to connect AirOps 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 AirOps with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index AirOps outputs into LlamaIndex

The `execute_workflow_sync` tool runs targeted workflows and returns structured data directly to your indexing pipeline. LlamaIndex takes this raw output, parses it into document nodes, and embeds them into your local vector store. This process ensures your retrieval-augmented generation (RAG) applications use fresh, live data instead of stale files. You can also use `list_apps` to discover available workflows dynamically. Your agent checks the metadata, runs the correct app, and indexes the results on the fly. This MCP setup keeps your data pipeline fully automated.

Query and update vector stores with this MCP Server

The `search_memory_store` tool queries your remote AirOps vector database to retrieve semantically relevant context. Your LlamaIndex agent combines these results with your local indexes to construct highly accurate prompts. If the agent uncovers new facts during a run, it writes them back instantly using `add_memory_document`. This bi-directional memory sync prevents hallucinations by grounding your model in verified facts. Instead of guessing, your agent searches past sessions and live databases to find concrete answers. Your applications become significantly more reliable as a result.

Inspect AirOps workflow metadata and execution states

The `get_app_details` tool fetches metadata for any registered workflow so your agent understands its inputs and outputs. When running complex processes, `get_execution_status` tracks the progress of background jobs. If a process hangs or runs too long, the agent invokes `cancel_execution` to free up resources. This deep inspection capability allows LlamaIndex to build self-correcting query engines. The engine reads the app details, structures the payload correctly, and monitors the run to completion. You get a resilient data pipeline that handles errors gracefully.

Setup guide

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

Install the MCP tool package via pip first. Then, instantiate the BasicMCPClient with your endpoint and wrap it in McpToolSpec. Finally, call the async tool list method and pass those tools to your FunctionAgent.

Yes, you can feed execution logs and memory documents directly into your LlamaIndex vector index. Your agent uses semantic search to query these past runs, ensuring it learns from previous workflow executions.

Your agent uses the `upload_file` tool to send local documents directly to the remote server. Once uploaded, these files are processed and indexed, making them immediately available for workflow runs or memory searches.

Yes, you can pass an allowed tools filter when defining your tool spec. This restricts the agent to specific operations, like only allowing memory searches while blocking workflow executions.

Every file uploaded via `upload_file` is encrypted at rest using AES-256 encryption. Vinkius processes all tool calls within ephemeral V8 isolates that destroy all temporary data immediately after execution. Your search queries and document contents are never exposed to external networks.

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