Puppeteer
This MCP server provides web screenshot capabilities using Puppeteer, enabling AI assistants to capture full-page screenshots at multiple viewport breakpoints (mobile, tablet, desktop) with comprehensive error monitoring and optimization features. Built with TypeScript and the MCP SDK, it offers a single screenshot tool that handles responsive design testing by automatically capturing images at different screen widths, includes detailed page error collection (JavaScript errors, console messages, network failures, CORS issues), supports both PNG and JPEG formats with quality controls, implements image optimization through width clipping for large viewports, and provides rich metadata including load times, actual content dimensions, and error summaries. The implementation features browser instance reuse for performance, configurable wait conditions for dynamic content, and detailed error reporting with categorization by type and severity level, making it valuable for web developers, QA teams, and designers who need automated visual testing, responsive design validation, and comprehensive page health monitoring through AI-assisted workflows.
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
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/hushaudio/puppeteermcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Puppeteer 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.