test driven development
A test-first workflow for turning a specific behavior requirement into an observable failing case and a focused implementation.
Repository star change: +698 over 26.7 hours. 2026-11-01
An MCP browser-automation connection for inspecting page structure and performing reviewable actions in a controlled browser session.
The checked registry entry declares the @playwright/mcp npm package and stdio transport. The repository explains browser interaction through structured accessibility snapshots. This supports an agent's iterative inspection loop, while the publisher separately discusses CLI-and-skill approaches for other coding workflows. These routes have different context and state tradeoffs.
A developer who needs to reproduce a browser task, inspect a live interface or validate a small page change. Define the target URL and permitted actions before connecting a session, particularly when the browser can reach signed-in services.
The source lists Node.js and MCP-client requirements. A browser connection can expose page content and perform actions; an accessibility snapshot is not a sandbox or a security boundary. Use a clean session and synthetic data for the first test.
Follow the source's client-specific setup and choose the intended package snapshot. Open a disposable test page, inspect its visible state and perform one reversible interaction. Keep publication, authentication changes and sensitive submissions under their own authorization.
Check that the observed page matches the intended session, the action produces the expected visible result and a failed interaction is reported. This catalog assessment did not launch a browser through the server or execute its package.
claude-code, codex, cursor, github-copilot
Repository setup documentation; protocol compatibility is not a runtime test
The publisher README lists Node.js 18 or newer and an MCP-capable client. Review the currently supported runtime and browser setup for your environment. Use a disposable browser session.
Illustrative stdio JSON using the publisher-documented npx route and the exact package version declared by this registry snapshot. Adapt the container key to your client; Codex configuration uses its own format. The package has not been installed or executed here.
{"mcpServers":{"playwright":{"command":"npx","args":["@playwright/mcp@0.0.84"]}}}Use your agent’s MCP settings and the publisher’s exact setup. Match the declared transport and package version. Credentials belong in your client’s supported secret storage. No command on this page is run by AI Craft Pad.
@playwright/mcp · version 0.0.84 · stdio · runtime Unknown
Unknown; source software and connected services may have separate terms.
Unknown — no runtime security assessment.
Only sanitized manifest/registry metadata and bounded documentation are inspected. Package code, transitive dependencies, hooks and remote services have not been audited. Review access before use.
Category-based discovery suggestions. Review functional overlap; these combinations have not been integration-tested.
A test-first workflow for turning a specific behavior requirement into an observable failing case and a focused implementation.
Repository star change: +698 over 26.7 hours. 2026-11-01
A completion-check workflow that ties a claim such as fixed, passing or deployed to fresh evidence from the relevant system.
Repository star change: +698 over 26.7 hours. 2026-11-01
A browser-testing workflow with Playwright-oriented examples and server-lifecycle helpers for checking local web application behavior.
Repository star change: +586 over 26.7 hours. 2026-11-01
Category-based discovery suggestions. Review functional overlap; these combinations have not been integration-tested.
A Claude Code plugin for choosing and reviewing property-based tests, including counterexample triage across several language ecosystems.
Explore math-olympiad as an agent plugin package for testing & qa. Review its supported format, bundled components and setup requirements before installing.
Explore agent-regression-evals as an agent plugin package for testing & qa. Review its supported format, bundled components and setup requirements before installing.
Category-based discovery suggestions. Review functional overlap; these combinations have not been integration-tested.
Explore air as an MCP connection for testing & qa. Compare the declared transport, package requirements and source evidence before connecting an agent.
Explore 0s and 1s CIS calculators as an MCP connection for testing & qa. Compare the declared transport, package requirements and source evidence before connecting an agent.
Explore 369 Meter — pay-per-call APIs for agents (x402) as an MCP connection for testing & qa. Compare the declared transport, package requirements and source evidence before connecting an agent.
Choose a complementary capability only after checking for duplicated permissions and bundled connections. Agent Stacks explain the roles and validation steps; they are proposals, not tested integrations.
Build a stack for your task · Related AI guides · Report a correction