How to Use the Azure Log Analytics Workspace MCP in LangChain

Q: How do I connect LangChain to Azure Log Analytics Workspace?

Install langchain-mcp-adapters. Set up a MultiServerMCPClient pointing to your Vinkius endpoint, fetch the tools, and bind them to your agent.

Give your LangChain agents direct, secure access to your Azure telemetry through a single MCP connection.

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 LangChain

Create your Vinkius account to connect Azure Log Analytics Workspace to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

KQL Execution in LangChain

By invoking the `query_logs` tool, your ReAct agents pull raw observability data to make routing decisions. They write the KQL operations, and the engine handles the table scoping automatically. You get real-time metrics directly inside your reasoning loop. You chain this output directly into your next step. Grab error spikes from the last hour, pass that text blob to a summarizer, and pipe the result into a Jira ticket creator. LangSmith traces the entire flow, so you see exactly how many tokens the KQL response consumed.

Table-Agnostic Querying

Security teams appreciate how the `query_logs` tool restricts operations to a single authorized table by design. Your agent just sends the filtering logic, like `| where TimeGenerated > ago(1h) | limit 10`, without ever knowing the table name. It focuses strictly on the data. That constraint keeps your architecture predictable. You drop the tool into a specific LangGraph node, knowing it cannot accidentally scan your entire Azure environment. It fails safe if the agent tries to overstep.

Observability Pipelines

Your LangChain setup can cross-reference infrastructure errors with customer support tickets by invoking the `query_logs` tool. The agent pulls the server logs, sees a memory spike, and decides to check the database metrics next. It builds a complete diagnostic picture. Building these diagnostic workflows used to require custom API wrappers and messy authentication logic. Now you just initialize `MultiServerMCPClient`, pass the MCP endpoint, and let the agent figure out the correlation.

Setup guide

Set up Azure Log Analytics Workspace MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Azure Log Analytics Workspace tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "azure-log-analytics-workspace-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Azure Log Analytics Workspace transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters`. Set up a `MultiServerMCPClient` pointing to your Vinkius endpoint, fetch the tools, and bind them to your agent.

No, this specific integration targets a single pre-configured table. The agent only provides the KQL operations, ensuring it stays within authorized boundaries.

Any valid Kusto operation that follows a table declaration works. Just start with the pipe operator, like `| count`, and the engine handles the rest.

LangSmith automatically traces every MCP tool invocation. You will see the exact execution time and token usage for each log retrieval step.

Vinkius runs the connection in an ephemeral V8 Isolate sandbox. Your Azure infrastructure logs pass directly to your agent through a zero-trust tunnel and are never stored 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