Safari Screenshot
This MCP server, developed by Roger Heykoop, provides a tool for capturing screenshots using Safari on macOS. Built with TypeScript and leveraging the Model Context Protocol SDK, it enables AI assistants to automate the process of taking web page screenshots. The implementation focuses on utilizing Safari's native capabilities on macOS, offering a lightweight alternative to browser automation tools like Puppeteer. It's particularly useful for developers and QA teams who need to integrate automated screenshot capture into their workflows, enabling use cases such as visual regression testing, web archiving, and content verification without manual intervention or the overhead of full browser automation frameworks.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Safari Screenshot 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.