Bietet KI-Assistenten Tools für die Entwicklung auf Arm-Architektur, die Code-Migration von x86 und die Analyse der Assembly-Performance.
Auch bekannt als arm/mcp, mcp
- Stars
- 95
- Tools
- 7
- Downloads, 30 Tage
- —
- Neueste Version
- 2.4.0
- Letzter Commit
- 15. Nov. 2026
- Lizenz
- Apache-2.0
Was ist Arm MCP?
Bietet KI-Assistenten Tools für die Entwicklung auf Arm-Architektur, die Code-Migration von x86 und die Analyse der Assembly-Performance. Er stellt 7 Tools bereit, etwa knowledge_base_search, check_image, sysreport_instructions.
Zusammenfassung generiert aus dem README des Projekts
Über Arm MCP server
Entwickler, die Anwendungen von der x86- auf die Arm-Architektur migrieren, können diesen Server nutzen, um komplexe Übergangstasks zu automatisieren. Er stellt KI-Assistenten spezialisierte Tools für die Code-Migrationsanalyse, die Auswertung der Assembly-Performance und den Abruf technischer Dokumentationen zur Verfügung. Durch die Integration mit einem MCP-kompatiblen Client wie Claude Code, GitHub Copilot oder Gemini CLI ermöglicht der Server es einer KI, als spezialisierter Experte für die Arm-Entwicklung zu agieren.
Der Server läuft in einem Docker-Container und benötigt Docker mit Buildx-Support, um zu funktionieren. Nutzer müssen ihren lokalen Workspace via Volume Mounts in den Container einbinden, damit die KI auf die Projektdateien zugreifen kann. Er enthält spezifische Tools wie migrate-ease zum Scannen von C++, Python, Go, JavaScript- und Java-Codebases, Skopeo zur Inspektion von Docker Image Architekturen und LLVM-MCA zur Analyse der Assembly-Performance. Technische Anfragen werden über eine Knowledge-Base-Suche beantwortet, die Arm Intrinsics, Software-Kompatibilität und Lernressourcen abdeckt.
Was du damit machen kannst
- 1Technische Dokumentation durchsuchenFühre semantische Suchen in der Arm-Dokumentation und bei Intrinsics durch, um spezifische technische Informationen zu finden.
- 2Assembly-Performance analysierenEvaluiere die Performance von Assembly-Code mithilfe spezialisierter LLVM-Tools.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du Arm MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenArm MCP in Claude Code installieren
$ claude mcp add mcp -- docker run -i --rm docker.io/armlimited/arm-mcp:2.4.0Arm MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/armlimited/arm-mcp:2.4.0"
]
}
}
}Arm MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/armlimited/arm-mcp:2.4.0"
]
}
}
}Arm MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"mcp","type":"stdio","command":"docker","args":["run","-i","--rm","docker.io/armlimited/arm-mcp:2.4.0"]}'Arm MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/armlimited/arm-mcp:2.4.0"
]
}
}
}Arm MCP in Codex installieren
$ codex mcp add mcp -- docker run -i --rm docker.io/armlimited/arm-mcp:2.4.0Arm MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.mcp] command = "docker" args = ["run", "-i", "--rm", "docker.io/armlimited/arm-mcp:2.4.0"]
Arm MCP in Gemini CLI installieren
$ gemini mcp add -s user mcp docker -- run -i --rm docker.io/armlimited/arm-mcp:2.4.0Arm MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/armlimited/arm-mcp:2.4.0"
]
}
}
}Von HostedMCP gestartet am 16. Nov. 2026
Wir haben diesen Befehl für docker.io/armlimited/arm-mcp:2.4.0 2.4.0 in einem isolierten Container ohne Netzwerk und ohne Schlüssel ausgeführt. Er hat geantwortet und 7 Tools gelistet.
Arm MCP tools 7
Vom Server mit tools/list gelesenknowledge_base_searchIf a user asks to migrate a codebase to Arm, strongly consider using this tool as a part of your strategy. Searches an Arm knowledge base of learning resources, Arm intrinsics, and software version compatibility using semantic similarity. Given a natural language query, returns a list of matching resources with URLs, titles, and content snippets, ranked by relevance. Useful for finding documentation, tutorials, or version compatibility for Arm migrations. Returned URLs may include tracking query parameters such as utm_source=arm-mcp and URL fragments. When sharing or citing returned URLs, preserve each URL exactly as returned, including query parameters and fragments; do not remove, normalize, shorten, or rewrite them. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context.
check_imageCheck Docker image architectures. Provide a Docker image reference such as nginx:latest and get a report of supported architectures. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context.
sysreport_instructionsProvides instructions for installing and using sysreport, a tool that obtains system information related to system architecture, CPU, memory, and other hardware details. For accurate host hardware data, review the commands with the user before running sysreport on the host system; host execution is outside container isolation.
migrate_ease_scanIf a user asks to migrate a codebase to Arm, strongly consider using this tool as a part of your overall strategy. Run a migrate-ease scan against the container-mounted workspace or a remote Git repo. Supported scanners: cpp, python, go, js, java. Returns stdio, output file path, parsed JSON when requested, and cleans up the output file before returning. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context. The scanner can take 60+ seconds depending on codebase size, so if the tool times out, tell the user to increase the timeout in the MCP server configuration.
apx_recipe_runRun a sample workload on the given target using a Performix recipe, and interpret the results. Some example user requests: - 'Help my analyze my code's performance.' - 'Find the code hotspots in my application.' If you do not know which recipe to use, use 'code_hotspots'. Ask the user if they want to run on localhost or a remote machine. If remote, then ask for the IP address of the remote machine. This tool is run within Docker. Do not try to run apx on the local machine. If the user is trying to connect to localhost, remember that from within the container, localhost is the container itself. Instead, use the host's IP address, which is usually 172.17.0.1. IMPORTANT NOTE: In order to run the intruction_mix, cpu_microarchitecture, memory_access or all recipes, the target machine must have access to all PMU counters on the machine. If not, then only code_hotspots can be run.
skopeoIf a user asks to migrate a codebase to Arm, strongly consider using this tool as a part of your overall strategy. This is a container image architecture inspector: Inspect container images remotely without downloading to check architecture support (especially ARM64 compatibility). Useful before migrating workloads to ARM-based infrastructure. Set 'image' (e.g. nginx:latest), optional 'transport' (docker, oci, dir), and 'raw' to get detailed manifest data. Shows available architectures, OS support, and image metadata. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context.
mcaAssembly Code Performance Analyzer: Analyze assembly code to predict performance on different CPU architectures and identify bottlenecks. Helps optimize code before migrating between processor types (x86 to ARM64). Estimates Instructions Per Cycle (IPC), execution time, and resource usage. Accepts 'input_path' (assembly/object file), optional 'triple' (target architecture), 'cpu' (specific processor model), and extra analysis arguments. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context.
| knowledge_base_search | If a user asks to migrate a codebase to Arm, strongly consider using this tool as a part of your strategy. Searches an Arm knowledge base of learning resources, Arm intrinsics, and software version compatibility using semantic similarity. Given a natural language query, returns a list of matching resources with URLs, titles, and content snippets, ranked by relevance. Useful for finding documentation, tutorials, or version compatibility for Arm migrations. Returned URLs may include tracking query parameters such as utm_source=arm-mcp and URL fragments. When sharing or citing returned URLs, preserve each URL exactly as returned, including query parameters and fragments; do not remove, normalize, shorten, or rewrite them. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context. | |
| check_image | Check Docker image architectures. Provide a Docker image reference such as nginx:latest and get a report of supported architectures. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context. | |
| sysreport_instructions | Provides instructions for installing and using sysreport, a tool that obtains system information related to system architecture, CPU, memory, and other hardware details. For accurate host hardware data, review the commands with the user before running sysreport on the host system; host execution is outside container isolation. | |
| migrate_ease_scan | If a user asks to migrate a codebase to Arm, strongly consider using this tool as a part of your overall strategy. Run a migrate-ease scan against the container-mounted workspace or a remote Git repo. Supported scanners: cpp, python, go, js, java. Returns stdio, output file path, parsed JSON when requested, and cleans up the output file before returning. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context. The scanner can take 60+ seconds depending on codebase size, so if the tool times out, tell the user to increase the timeout in the MCP server configuration. | |
| apx_recipe_run | Run a sample workload on the given target using a Performix recipe, and interpret the results. Some example user requests: - 'Help my analyze my code's performance.' - 'Find the code hotspots in my application.' If you do not know which recipe to use, use 'code_hotspots'. Ask the user if they want to run on localhost or a remote machine. If remote, then ask for the IP address of the remote machine. This tool is run within Docker. Do not try to run apx on the local machine. If the user is trying to connect to localhost, remember that from within the container, localhost is the container itself. Instead, use the host's IP address, which is usually 172.17.0.1. IMPORTANT NOTE: In order to run the intruction_mix, cpu_microarchitecture, memory_access or all recipes, the target machine must have access to all PMU counters on the machine. If not, then only code_hotspots can be run. | |
| skopeo | If a user asks to migrate a codebase to Arm, strongly consider using this tool as a part of your overall strategy. This is a container image architecture inspector: Inspect container images remotely without downloading to check architecture support (especially ARM64 compatibility). Useful before migrating workloads to ARM-based infrastructure. Set 'image' (e.g. nginx:latest), optional 'transport' (docker, oci, dir), and 'raw' to get detailed manifest data. Shows available architectures, OS support, and image metadata. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context. | |
| mca | Assembly Code Performance Analyzer: Analyze assembly code to predict performance on different CPU architectures and identify bottlenecks. Helps optimize code before migrating between processor types (x86 to ARM64). Estimates Instructions Per Cycle (IPC), execution time, and resource usage. Accepts 'input_path' (assembly/object file), optional 'triple' (target architecture), 'cpu' (specific processor model), and extra analysis arguments. Includes 'invocation_reason' parameter so the model can briefly explain why it is calling this tool to provide additional context. |
Automatisierte Checks
Geluften am 16. Nov. 2026Vollständiger Bericht →Noch nicht verifiziert. Ein Server benötigt einen Score von 80, keine kritischen Befunde und genug Daten für unsere Prüfung. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbararm/mcp is public and reachablegithub.com/arm/mcp ↗Bestanden
- Paket nennt dieses Repository als QuelleNicht geprüft
- Build-Provenienz (Sigstore-Attestierung)Nicht geprüft
- Open Source Lizenz (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-11-15github.com/arm/mcp ↗Bestanden
- OpenSSF ScorecardOpenSSF Scorecard 9.0 / 10; weakest: Fuzzing 0, CII-Best-Practices 2, Contributors 3scorecard.dev/viewer/?uri=github.com/arm/mcp ↗Bestanden
- Package-Name ähnelt keinem populären PackageNicht geprüft
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
- Keine versteckten Anweisungen an das Modell7 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNo tool named like delete, drop or execBestanden
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenArm MCP Server
An MCP server providing AI assistants with tools and knowledge for Arm architecture development, migration, and optimization.
Using the Arm MCP Server
If your goal is to migrate an application from x86 to Arm as quickly as possible, start here:
Automate x86-to-Arm application migration using Arm MCP Server
Features
This MCP server equips AI assistants with specialized tools for Arm development:
- Knowledge Base Search: Keyword and semantic search across Arm documentation, learning resources, intrinsics, and software compatibility information, with technical-name aliases
- 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
Pre-Built Image
If you would prefer to use a pre-built, multi-arch image, the official image can be found in Docker Hub here: armlimited/arm-mcp:latest
Prerequisites
- Docker with Buildx support
- An MCP-compatible AI assistant client (e.g. GitHub Copilot, Kiro CLI, Codex CLI, Claude Code, etc)
Quick Start
1. Build the Docker Image
From the root of this repository:
docker buildx build -f mcp-local/Dockerfile -t armlimited/arm-mcp . --load
This builds for the Docker host's native architecture. The release workflow is responsible for explicit multi-architecture builds.
For local development builds, see the Quick Local Development Builds section in CONTRIBUTING.md.
2. Configure Your MCP Client
Choose the configuration that matches your MCP client:
Claude Code
Add to .mcp.json in your project:
{
"mcpServers": {
"arm-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--pull=always",
"-v", "/path/to/your/workspace:/workspace",
"armlimited/arm-mcp"
]
}
}
}
GitHub Copilot (VS Code)
Add to .vscode/mcp.json in your project, or globally at ~/Library/Application Support/Code/User/mcp.json (macOS):
{
"servers": {
"arm-mcp": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--pull=always",
"-v", "/path/to/your/workspace:/workspace",
"armlimited/arm-mcp"
]
}
}
}
The easiest way to open this file in VS Code for editing is command+shift+p and search for
MCP: Open User Configuration
AWS Kiro CLI
Add to ~/.kiro/settings/mcp.json:
{
"mcpServers": {
"arm-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--pull=always",
"-v", "/path/to/your/workspace:/workspace",
"armlimited/arm-mcp"
],
"timeout": 60000
}
}
}
Gemini CLI
It is recommended to use a project-local configuration file to ensure the relevant workspace is mounted.
Add to .gemini/settings.json in your project root:
{
"mcpServers": {
"arm-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--pull=always",
"-v", "/path/to/your/workspace:/workspace",
"armlimited/arm-mcp"
]
}
}
}
MCP Clients using TOML format (e.g. Codex CLI)
[mcp_servers.arm-mcp]
command = "docker"
args = [
"run",
"--rm",
"-i",
"--pull=always",
"-v", "/path/to/your/workspace:/workspace",
"armlimited/arm-mcp"
]
Note: Replace /path/to/your/workspace with the actual path to your project directory that you want the MCP server to access.
3. Restart Your MCP Client
After updating the configuration, restart your MCP client to load the Arm MCP server.
Logging
Depending on usage, the server may write two log files under /workspace. With the
configuration examples above, these files appear in the project directory on
your computer:
mcp-traffic.jsonlrecords when tools are used, the inputs provided, and the reason for each tool call. It also records results from knowledge base searches.error_logging.yamlrecords details about errors encountered by the server. This information can help with troubleshooting.
These logs may contain information from your project and tool requests. Review their contents before sharing them.
Development and contributing
See CONTRIBUTING.md for repository structure, integration testing, reproducible build inputs, runtime-egress validation, dependency updates, and release workflows.
Troubleshooting
Accessing the Container Shell
To debug or explore the container environment:
docker run --rm -it --entrypoint /bin/bash armlimited/arm-mcp
Common Issues
- Timeout errors during migration scans: Increase the
timeoutvalue in your MCP client configuration (e.g.,"timeout": 120000for 2 minutes) - Empty workspace: Ensure your volume mount path is correct and the directory exists
- Architecture mismatches: Confirm that the local image matches the Docker host's native architecture; use the release workflow for explicit cross-platform builds.
Suspected vulnerabilities must not be reported in public issues. See the Arm MCP security policy and report them via Arm PSIRT.
License
Copyright © 2026, Arm Limited and Contributors. All rights reserved.
Licensed under the Apache License, Version 2.0. See LICENSE for details.
Arm MCP Fragen
Wie füge ich Arm MCP zu Claude Code hinzu?
Führe claude mcp add mcp -- docker run -i --rm docker.io/armlimited/arm-mcp:2.4.0 in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich Arm MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet Arm MCP?
Er stellt 7 Tools bereit, darunter knowledge_base_search, check_image, sysreport_instructions, migrate_ease_scan, apx_recipe_run.
Wie kann ich eine Anwendung von x86 nach Arm migrieren?
Du kannst den Arm MCP Server nutzen, um den Migrationsprozess mithilfe spezialisierter Tools für Code-Analyse und Kompatibilitäts-Scans zu automatisieren.
Wo finde ich das offizielle Docker Image?
Das offizielle Multi-Arch-Image ist auf Docker Hub unter armlimited/arm-mcp:latest verfügbar.