Item detail
github.com

agent-sh/computer-use-linux

agent-sh/computer-use-linux is a mcp server that RepoRadar is tracking in its Computer Use / MCP section, currently rated Gold tier with a 'worth watch' verdict. Its strongest signal is workflow potential, scored 9.0 out of 10.

Score8.2
Popularity215.0
Riskhigh
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum7.0
Maturity8.9
Open-source/build8.4
Evidence8.0
Workflow potential9.0
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for builders who specifically need Linux desktop automation for agents and want a more honest, infrastructure-grade computer-use surface than macOS-only demos or OCR-first hacks.

Who should use it

Agent-tool builders who need Linux desktop control through a standard MCP surfaceHermes, Claude, or Codex users on Linux who want a supported path for local computer usePlatform teams testing computer-use automation against GNOME, KDE, Hyprland, i3, or COSMIC sessionsDevelopers who want semantic selectors and a readiness report instead of relying entirely on pixel coordinates

Who should skip it

Pass on agent-sh/computer-use-linux if your environment cannot support the access controls and sandboxing this risk profile requires.

About this signal

agent-sh/computer-use-linux is tracked by RepoRadar as a mcp server in the Computer Use / MCP section. It was first seen on 2026-06-26 and last updated on 2026-06-26. The current verdict is 'worth watch' with a Gold tier and moderate setup difficulty. The standout signals for agent-sh/computer-use-linux are workflow potential (9.0) and maturity (8.9), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned agent-sh/computer-use-linux a composite score of 8.2 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 215.0 and never affects the composite score or tier. The risk label of 'high' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

This server can inspect live desktop state and invoke real clicks, key presses, drags, and text input, so it should be treated as full local computer control rather than a passive MCP data source; Setup can install accessibility settings and GNOME window-targeting helpers, which means it changes host desktop configuration as part of the enablement path; Any MCP host that exposes the destructive tools without strong user confirmation could let an agent submit, delete, purchase, or overwrite data in whatever application is in focus.

Evidence links
Closest alternatives / related signals
mcpcomputer-uselinuxwaylandrustautomationdesktop-controlmit