How to Use the Azure Log Analytics Workspace MCP in Vercel AI SDK

Q: How does the Vercel AI SDK handle query results from the Azure Log Analytics Workspace?

It streams them. When you call streamText with the querylogs tool, the log data is sent back in chunks as it's found, letting you render results in your UI immediately.

Q: What kind of KQL can I run against my Azure Log Analytics Workspace with the Vercel AI SDK?

You can run standard KQL operations like where, summarize, and limit. Just remember not to include the table name in your query string; the server adds it for you.

Stream Azure log data directly into your React components with the Vercel AI SDK. No loading spinners, just live results.

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 Vercel AI SDK

Create your Vinkius account to connect Azure Log Analytics Workspace to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Live Log Viewer

This MCP server gives your Vercel AI SDK app one tool: `query_logs`. Use it to build a front-end that shows Azure log entries appearing in real-time. Your KQL query runs, and the results stream directly into your UI components. Forget polling or waiting for a full dataset to load. As the `query_logs` tool finds entries, the AI SDK pipes them straight to your app. It's perfect for creating dashboards or incident response screens where your users see what's happening, as it happens.

Secure, Read-Only Access

Give your agent a keyhole, not the keys to the kingdom. This server is locked down to a single Azure Log Analytics table and one read-only operation. You're not exposing your entire Azure environment. Your AI client can run a `query_logs` KQL query and nothing else. This narrow focus makes it safe to build user-facing observability tools without worrying about accidental writes or exposing sensitive configurations. It's a secure-by-design approach.

Query Logs in Your AI SDK App

The `query_logs` tool becomes a native function in your TypeScript code. You call it, pass your KQL string, and process the streaming response. It fits right into the AI SDK model you already know. This isn't just about viewing logs. You can chain actions together. For instance, have your agent query for errors with `query_logs`, then use a different MCP tool to create a GitHub issue with the details. The AI SDK manages the tool calls; you just define the logic.

Setup guide

Set up Azure Log Analytics Workspace MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Azure Log Analytics Workspace tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Azure Log Analytics Workspace transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

It streams them. When you call `streamText` with the `query_logs` tool, the log data is sent back in chunks as it's found, letting you render results in your UI immediately.

You can run standard KQL operations like `where`, `summarize`, and `limit`. Just remember not to include the table name in your query string; the server adds it for you.

Yes, that's exactly what this is for. Your React or Next.js app can use the AI SDK to continuously stream data from `query_logs`, updating the UI as new errors are logged.

No. The MCP server connects to Azure using a single Vinkius endpoint token. Your frontend code never touches Azure service principals or keys. It's much simpler and more secure.

Absolutely not. The server is stateless. It acts as a pass-through, forwarding your KQL query to Azure and streaming the resulting log data directly to your Vercel AI SDK client. Your data is only ever in transit.

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