Run browser and API automation through the Playwright MCP server
Expose Playwright browser and API automation commands to MCP-capable agents for supervised test workflows.
npx skills add agentskillexchange/skills --skill run-browser-and-api-automation-through-the-playwright-mcp-server
Use this skill when an operator needs an MCP-capable agent to run Playwright-backed browser or API automation with observable commands and reviewable outputs. The workflow is to connect the MCP server, open or navigate pages, perform test or inspection actions, capture screenshots or API responses, and use the results for debugging or regression checks. Invoke it instead of normal Playwright scripting when the agent needs a standardized tool surface through MCP. Do not use it as a broad Playwright tutorial or as unsupervised web automation. The scope boundary is MCP-mediated browser and API automation using the upstream mcp-playwright server.
What this skill actually does
Inputs and prerequisites: Node.js, Playwright browsers, an MCP-capable client such as Claude Desktop, Cursor, Cline, or compatible agent runtime.
Setup notes: Clone or install the MCP Playwright server as documented upstream, install Playwright browsers, register the server with an MCP client, and run browser/API automation commands through the client.
Source and verification boundary: use https://github.com/executeautomation/mcp-playwright as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.