Screenshot
This MCP server provides AI assistants with website screenshot capture capabilities, built by Up North Media using Node.js with Puppeteer for browser automation and Sharp for image processing. The implementation offers three core tools: full-page screenshot capture with device presets (mobile, tablet, desktop), element-specific screenshots using CSS selectors, and device preset listing, all featuring advanced wait conditions including network idle detection, custom delays, and automatic image resizing to stay within 8000x8000 pixel limits. Built with rate limiting, concurrent request management, sandboxed browser execution, and comprehensive error handling including URL validation and CSS selector sanitization, it serves web development workflows requiring visual testing and documentation, UI/UX analysis through conversational interfaces, and automated screenshot generation for quality assurance without direct browser automation knowledge.
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
- Repository
- github.com/upnorthmedia/screenshotmcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve 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.