How to Use the Azure Log Analytics Workspace MCP in Windsurf

Q: How do I connect the Azure Log Analytics Workspace MCP Server to Windsurf?

Open your /.codeium/windsurf/mcpconfig.json file and add the server configuration under the mcpServers key. Alternatively, use the Settings UI under Cascade, paste the Vinkius URL, and click Refresh in the MCP panel to let Cascade auto-discover the querylogs tool.

Q: Can Windsurf Cascade write logs back to my Azure Log Analytics Workspace?

No, this server only supports read operations. The querylogs tool is strictly for executing Kusto queries, meaning Windsurf can analyze your logs but cannot modify, delete, or inject new records into your Azure tables.

Q: Why does my KQL query fail when I include the table name in Cascade?

The querylogs tool expects you to omit the table name entirely. Start your query directly with Kusto operations like where TimeGenerated > ago(1h) because the backend automatically prepends the correct table name before execution.

Get live Azure telemetry directly inside Windsurf and let Cascade autonomously diagnose system failures.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run KQL queries directly inside Windsurf Cascade

The `query_logs` tool executes Kusto operations against your designated Azure log table without leaving your IDE. Cascade uses this tool to grab raw telemetry, parsing through timestamps and error codes to map out system behavior. Because the server automatically prepends the authorized table name, Cascade only needs to pass the filtering operations like `| where TimeGenerated > ago(1h)`. This setup lets Cascade chain log analysis with code fixes. When an exception pops up in your terminal, Cascade runs a query, identifies the failing container, finds the buggy file, and writes the patch in one autonomous run.

Let this MCP Server drive autonomous incident triage

The `query_logs` tool feeds real-time telemetry straight into Windsurf's planning engine. Cascade scans your log tables for recent anomalies, filtering out the noise to pinpoint the exact moment your production service started throwing 500 errors. You don't have to copy-paste stack traces into a browser window anymore. Cascade triggers the KQL query, reads the structured output, and immediately starts editing the affected files in your workspace.

Safe telemetry querying without table leakage

The `query_logs` tool protects your database schema by hiding the root table name from the client's direct input. Windsurf sends raw KQL operations, and the backend handles the rest, ensuring your agent never targets unauthorized tables. This design keeps your workspace secure while giving Cascade the granular access it needs to debug complex microservices using this MCP server. You get precise diagnostics without exposing your entire Azure data infrastructure.

Setup guide

Set up Azure Log Analytics Workspace MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Azure Log Analytics Workspace MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Azure Log Analytics Workspace payment history." If connected, Cascade will call the Azure Log Analytics Workspace tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "azure-log-analytics-workspace-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Open your `~/.codeium/windsurf/mcp_config.json` file and add the server configuration under the `mcpServers` key. Alternatively, use the Settings UI under Cascade, paste the Vinkius URL, and click Refresh in the MCP panel to let Cascade auto-discover the `query_logs` tool.

No, this server binds to one specific pre-configured table on the Vinkius platform. When Windsurf calls the `query_logs` tool, the server automatically prepends that target table name to your KQL operations, keeping queries fast and scoped.

No, this server only supports read operations. The `query_logs` tool is strictly for executing Kusto queries, meaning Windsurf can analyze your logs but cannot modify, delete, or inject new records into your Azure tables.

The `query_logs` tool expects you to omit the table name entirely. Start your query directly with Kusto operations like `| where TimeGenerated > ago(1h)` because the backend automatically prepends the correct table name before execution.

Yes, your log outputs pass through an ephemeral, zero-trust V8 Isolate sandbox on Vinkius. The server only reads the specific table logs configured, and no telemetry is stored or used for training models.

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