How to Use the Azure Log Analytics Workspace MCP in OpenAI Agents SDK

Q: How do I query logs using Azure Log Analytics Workspace with the OpenAI Agents SDK?

You initialize the MCP server using MCPServerStreamableHttp and pass it to your Agent constructor. The agent automatically discovers the querylogs tool. From there, your agent can run KQL operations like filtering or limiting results without knowing the underlying table name.

Q: How does tool caching work with Azure Log Analytics Workspace and OpenAI Agents SDK?

Set cacheToolsList=True when configuring your streamable HTTP server parameters. This prevents the OpenAI Agents SDK from querying the Vinkius endpoint for tool definitions on every single run, which speeds up your agent's response times.

Run safe KQL queries inside your production OpenAI Agents SDK pipelines with zero-config log access.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure Log Analytics Workspace MCP to OpenAI Agents SDK

Create your Vinkius account to connect Azure Log Analytics Workspace to OpenAI Agents SDK 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 Azure Log Analytics Workspace with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure Log Querying with OpenAI Agents SDK

Your production agents query logs directly via the `query_logs` tool without exposing database credentials. The agent sends KQL operations like filtering by timestamp, and Vinkius handles the connection to your Azure workspace. Because OpenAI Agents SDK has built-in guardrails, you can validate the KQL query before your agent runs it. This setup keeps your raw log table names hidden. The MCP server automatically prepends the authorized table name, so your agent only writes the operational KQL. You get clean log data sent straight into your agent's context window.

Trace KQL Agent Runs in Your OpenAI Dashboard

Debugging autonomous agents is a pain when they write bad queries. This MCP server integrates with your OpenAI Agents SDK tracing dashboard to show you every single KQL payload sent to `query_logs`. You see exactly what the agent searched for and how the workspace responded. If an agent gets stuck in a loop trying to find a specific error, you will catch it in the trace. You can also monitor latency to ensure your production pipelines do not stall during heavy log analysis tasks.

Multi-Agent Handoffs for Log Analysis

You don't want a single agent doing everything. Use the OpenAI Agents SDK to build a triaging agent that hands off to a specialized security agent when it detects anomalies using `query_logs`. The security agent runs deep diagnostics while the triage agent keeps monitoring. Setting this up takes seconds with Vinkius. Initialize `MCPServerStreamableHttp` in Python, pass it to your Agent constructor, and set `cacheToolsList=True` to keep tool discovery fast across your entire multi-agent network.

Setup guide

Set up Azure Log Analytics Workspace MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Azure Log Analytics Workspace tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Azure Log Analytics Workspace tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Azure Log Analytics Workspace tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Azure Log Analytics Workspace Agent",
            instructions="You have access to Azure Log Analytics Workspace tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Azure Log Analytics Workspace. 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 Azure Log Analytics Workspace 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 Azure Log Analytics Workspace MCP in OpenAI Agents SDK

You initialize the MCP server using `MCPServerStreamableHttp` and pass it to your Agent constructor. The agent automatically discovers the `query_logs` tool. From there, your agent can run KQL operations like filtering or limiting results without knowing the underlying table name.

Yes, the SDK's built-in guardrails validate any KQL operations before the `query_logs` tool executes them. You can inspect, modify, or block the agent's query payloads at runtime to prevent runaway resource usage.

Set `cacheToolsList=True` when configuring your streamable HTTP server parameters. This prevents the OpenAI Agents SDK from querying the Vinkius endpoint for tool definitions on every single run, which speeds up your agent's response times.

No, your agent must not include the table name. The MCP server automatically prepends the authorized table name to whatever KQL operations your agent sends to the `query_logs` tool.

Vinkius runs the server in an isolated, ephemeral V8 sandbox. Your workspace event logs are fetched over secure HTTPS and passed directly to your OpenAI Agents SDK runtime without being stored or cached on our infrastructure.

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