Arm MCP Server

Official Arm MCP server for code migration, optimization, and Arm architecture guidance

Local serverstdioPython

What is the Arm MCP server?

Most developer tooling work still happens through a UI a human drives. Arm MCP server moves it into the conversation instead. Official Arm MCP server for code migration, optimization, and Arm architecture guidance.

The short version

An MCP server providing AI assistants with tools and knowledge for Arm architecture development, migration, and optimization.

  • Knowledge Base Search — Semantic search across Arm documentation, learning resources, intrinsics, and software compatibility information
  • Code Migration Analysis — Scan codebases for Arm compatibility using migrate-ease (supports C++, Python, Go, JavaScript, Java)
  • Container Architecture Inspection — Check Docker image architecture support using integrated Skopeo and check-image tools
  • Assembly Performance Analysis — Analyze assembly code performance using LLVM-MCA
  • Arm Performix — Run APX recipe workflows against a target device over SSH to capture and analyze workload performance data
  • System Information — Instructions for gathering detailed system architecture information via sysreport

The tools it exposes

The server publishes 3 tools. What each one is for:

  • mcp — traffic.jsonl records when tools are used, the inputs provided, and the
  • server.py — Main FastMCP server with tool definitions
  • Dockerfile — Multi-stage Docker build

Getting it running

The server ships on a container image as armlimited/arm-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What it needs from you

  • Docker (with buildx support for multi-arch builds) - An MCP-compatible AI assistant client (e.g. GitHub Copilot, Kiro CLI, Codex CLI, Claude Code, etc)

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Arm's toolset — mcp, server.py, Dockerfile — is a fair guide to whether it matches your workflow. It is maintained by arm; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
mcptraffic.jsonl records when tools are used, the inputs provided, and the
server.pyMain FastMCP server with tool definitions
DockerfileMulti-stage Docker build

How to install the Arm MCP server

{
  "mcpServers": {
    "arm-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--pull=always",
        "-v", "/path/to/your/workspace:/workspace",
        "-v", "/path/to/your/ssh/private_key:/run/keys/ssh-key.pem:ro",
        "-v", "/path/to/your/ssh/known_hosts:/run/keys/known_hosts:ro",
        "armlimited/arm-mcp"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Docker (with buildx support for multi-arch builds) - An MCP-compatible AI assistant client (e.g. GitHub Copilot, Kiro CLI, Codex CLI, Claude Code, etc)

Example prompts to try

  • Use Arm to mcp.
  • Use Arm to server.py.
  • Use Arm to Dockerfile.

Frequently asked questions

It connects Arm to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (mcp, server.py, Dockerfile) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Arm directly.