Skip to main content
Glama
Sign In
playwright-e2e-mcp

playwright-e2e-mcp

by xsignon-secure
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to playwright-e2e-mcp

No user-submitted related servers found.

    Related Servers

    • playwright-e2e-mcp

      trajectiq-ai
      A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to run, debug, and inspect Playwright end-to-end tests, returning structured pass/fail stats, failure diagnostics with actionable fix hints, live DOM inspection, selector validation, visual diffs, and flakiness verdicts instead of raw test output.
      11
      1,816 npm
      MIT

    • tuxedo-qa

      jonathan-ponciano
      A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to create, run, autocorrect, and monitor Playwright tests for your app with a local dashboard, credential vault, and public status page.
      16
      MIT
    • QualityMax QA MCP

      QualityMax QA MCPofficial

      Quality-Max
      A
      license
      A
      quality
      B
      maintenance
      Enables coding agents to independently verify web changes by scanning pages, inspecting UI structure, generating Playwright reproductions, and executing tests with structured QA evidence.
      4
      85 npm
      4
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4/5.0

    Scored across 20 tools

    Disambiguation4/5

    Most tools target clearly distinct phases (run, inspect, generate, fix, audit), and the long descriptions actively spell out boundaries. A few pairs are genuinely adjacent and could still be mispicked: audit-tests vs check-test-change (both audit spec code), diagnose-flaky vs analyze-history (both about flakiness), and inspect-page vs validate-selector (both return verified locators for a live page).

    Naming Consistency4/5

    Nearly everything follows a predictable kebab-case verb_noun pattern (run-test, get-failure, audit-accessibility, suggest-fix). The only outlier is the bare verb 'quarantine', which is a minor deviation rather than a convention break.

    Tool Count4/5

    20 tools sits at the heavy end, but the domain genuinely spans running, debugging, auditing, generating, visual/a11y/perf checks, and session handling, so most tools earn their place. A few (audit-tests/check-test-change, inspect-page/validate-selector) could arguably merge, which keeps it from a 5.

    Completeness4/5

    Coverage of the E2E lifecycle is strong: run, list, inspect, generate, heal, bisect, flake-diagnose, history, quarantine, mocks, a11y, perf, visual, and login persistence. Minor gaps remain around directly editing/managing spec files or test config beyond generation, but no core workflow is a dead end.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Resources