MCP.Market

open-compute (computer-use) MCP server

by lukisch·io.github.lukisch/open-compute-mcp·v0.1.0-alpha.6·1 stars
No reviews yet

Model-agnostic computer-use MCP: screenshot, safety-gated actions, Windows UIA targeting.

A86/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A86/100

full report

Adoption
Growing

1 stars50 downloads/wk

Reviews

Write one

Nobody has reviewed open-compute (computer-use) yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

open-compute (computer-use) tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 3 days ago15/15
  • Maintainer identitynamespace and repository owner differ4/10
Overall 86/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How open-compute (computer-use) compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
86/100
higher than 75% of 4,464 AI and agents servers
GitHub stars
1
more than 50% of 2,697 AI and agents servers
Downloads a week
50
more than 44% of 1,515 AI and agents servers with a package

Install open-compute (computer-use) in Claude Code, Cursor or VS Code

Runs npx -y open-compute-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add open-compute-mcp -- npx -y open-compute-mcp
Add to Cursor

What the publisher says

From the open-compute (computer-use) repository's README, as published. We do not edit it. Read it on GitHub

open-compute-mcp

npm launcher for the open-compute MCP server — model-agnostic computer-use tools exposed over the Model Context Protocol (MCP).

[!IMPORTANT]

Local stdio only. Real capture and input require an interactive Windows

desktop session on the MCP client's own host. This launcher is not Glama-hostable;

a hosted "Deploy Server" flow cannot access your desktop.

Install it in a local MCP client instead.

EN | DE

📦 View on npm → • 📋 Security Policy • ⚖️ Licenses • 🤖 LLM Context (llms.txt)

Quick Navigation

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

open-compute (computer-use): common questions

Is open-compute (computer-use) MCP server safe?
Yes, by our scan: it is graded A (86/100). Read the open-compute (computer-use) safety report
How do I install open-compute (computer-use)?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does open-compute (computer-use) need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is open-compute (computer-use) maintained?
The last commit was 41 days ago (2026-09-22). The latest release is v0.1.0-alpha.6.
What can I use instead of open-compute (computer-use)?
Servers from other publishers that do the same job: Decionis MCP server, MCP Server for WinDbg Crash Analysis and Agent-Native Chat MCP server.
How does open-compute (computer-use) compare with other AI and agents MCP servers?
safety score 86/100 (higher than 75% of 4,464 AI and agents servers); github stars 1 (more than 50% of 2,697 AI and agents servers); downloads a week 50 (more than 44% of 1,515 AI and agents servers with a package). Full comparison.

Alternatives to open-compute (computer-use)

Same job from other publishers: the closest match first, then the best rated.

  • Decionis
    Authorize consequential AI agent actions before execution
    A
  • MCP Server for WinDbg Crash Analysis
    A Model Context Protocol server for Windows crash dump analysis using WinDbg/CDB
    A
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • Vibe Check
    Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety
    B

More from lukisch →