Desktop Automation
MCP Desktop Automation is a server that provides desktop automation capabilities using RobotJS and screenshot functionality, enabling AI assistants to control mouse movements, keyboard inputs, and capture screenshots. Developed by Adriano Bonat, the implementation exposes tools for screen capture, keyboard/mouse control, and screen size detection through a standardized interface that works with various MCP clients but is primarily tested with Claude Desktop. The server handles system-level permissions for screen capture and input simulation, making it valuable for users who want their AI assistant to interact directly with desktop applications without manual intervention.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- other
- Source
- PulseMCP
- Repository
- github.com/tanob/mcp-desktop-automation
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Desktop Automation from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.