PlayMCP (Playwright Browser Automation)
This MCP server provides comprehensive browser automation capabilities using Playwright, enabling AI assistants to interact with web pages through a full suite of browser controls including navigation, clicking, typing, scrolling, and screenshot capture. Built with TypeScript and offering both headless and visual browser modes with debug logging, it provides extensive page content extraction tools for HTML source, text content, links, images, forms, meta tags, scripts, and stylesheets, plus the ability to execute arbitrary JavaScript code on pages and return results. The implementation maintains browser state across operations, includes detailed error handling with helpful suggestions, and supports both standard MCP protocol and legacy command formats, making it valuable for web scraping, automated testing, form filling, content analysis, and any scenario where AI assistants need to programmatically interact with websites and extract structured data from web pages.
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/jomon003/playmcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve PlayMCP (Playwright Browser 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.