Generate Arm Performix AI insights in VS Code with Claude Code
Introduction
Understand the AI-assisted Arm Performix insight workflow
Configure the Arm Performix MCP server in Claude Code
Create an Arm Performix Code Hotspots run
Generate Arm Performix AI insights for a Code Hotspots run
Open the run in Arm Performix for deeper inspection
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

About this Learning Path

Skill level:  Introductory
Reading time:  20 min
Last updated:  30 Oct 2026
Skill level:
  Introductory
Reading time:
  20 min
Last updated:
  30 Oct 2026
Authors:Kieran Hejmadi, Arm
Julie Gaskin, Arm
Arm IP:Neoverse
Tags: Performance and Architecture Linux Arm Performix Claude Code Model Context Protocol Visual Studio Code
Authors:
  • Kieran Hejmadi, Arm
  • Julie Gaskin, Arm
Arm IP:
Neoverse
Tags:
Performance and Architecture Linux Arm Performix Claude Code Model Context Protocol Visual Studio Code

Who is this for?

This Learning Path is for software developers and performance engineers who want to optimize applications on Arm-based servers using Arm Performix.

What will you learn?

After completing this Learning Path, you'll be able to perform the following tasks:

  • Configure the Arm Performix Model Context Protocol (MCP) server for the Claude Code extension in Visual Studio Code (VS Code).
  • Verify that Claude Code can access Arm Performix recipes, targets, and runs.
  • Create a supported Code Hotspots run.
  • Generate an AI insight and validate its recommendations against profile evidence.

Prerequisites

Before starting, you'll need the following prerequisites:

  • An installation of Arm Performix version 2026.2.5 or later
  • A configured Arm Linux target with a workload to profile
  • VS Code, with the Claude Code extension version 2.1.261 or later installed to add MCP servers through the extension interface
  • Access to Claude Code through a Claude account, or an organization-approved Anthropic API key provided through the ANTHROPIC_API_KEY environment variable
  • Permission from your organization to share profile data, symbols, source and disassembly excerpts, and performance metrics with Claude Code

Summary

AI-assisted

This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
You’ll connect Claude Code in VS Code to the Arm Performix MCP server to generate an AI insight. First, you’ll choose an MCP configuration method and verify access to recipes and runs. You’ll then create or select a supported run, request an insight with its run ID, and open it in Arm Performix. Finally, you’ll identify the run and compare the recommendation with profile evidence.
Next