Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for builders who want computer-use workflows on Windows without building their own desktop automation bridge from scratch.
Where this stands now
CursorTouch/Windows-MCP ranks #42 of 2355 tracked Radar items by composite score (8.7 against a section median of 5.2). The section currently carries 1248 Bronze, 645 Gold, 462 Silver. RepoRadar has retained observations for this record since 2026-06-20 (100 days in the current window). Signal extremes versus the section: momentum at the 80th percentile.
Who should use it
Who should skip it
Pass on CursorTouch/Windows-MCP if your environment cannot support the access controls and sandboxing this risk profile requires.
About this signal
CursorTouch/Windows-MCP is tracked by RepoRadar as a developer tool in the Radar section. First seen 2026-06-20; the source record was last checked on 2026-06-20. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for CursorTouch/Windows-MCP are workflow potential (9.8) and practical usefulness (9.0), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The CursorTouch/Windows-MCP record combines a 8.7/10 composite score with separate popularity (74.0), risk (medium), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
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
The server can click, type, open apps, and move through local files on a live Windows session, so test it in a non-sensitive account or VM before trusting it with real work; Desktop automation on an authenticated machine can expose internal documents, secrets, or admin actions if the agent gets the wrong target window or prompt.