Skip to main content
Glama
contraliz

qa-mcp

by contraliz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to qa-mcp

No user-submitted related servers found.

    Related Servers

    • vouch

      hamza-paracha
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables coding agents to verify application changes by running browser workflows, executing independent state assertions, and producing replayable evidence.
      0
      MIT

    • flowcheck

      kadessovb02
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables coding agents to validate web pages and run repeatable JSON browser scenarios, returning pass/fail results with local Playwright evidence such as screenshots, traces, and JUnit XML.
      7 npm
      1
      Apache 2.0

    • weblab

      dittofleet
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents to drive real Chromium, WebKit, or Firefox browsers — opening named sessions, running ordered steps like clicks, typing, and assertions, and reading back text, console/network logs, and screenshots — so web apps can be tested and explored end to end. It starts and shares dev servers, attaches to already-running browsers, and can fake API responses or device settings.
      1 npm
      MIT

    • why-ui

      Yudis-bit
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables coding agents to inspect live browser runtime evidence, such as blocking elements and interaction surfaces, and to independently verify whether a code fix resolved the issue.
      9 npm
      1
      MIT
    Deploy Server
    Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

    TDQS

    B3.3/5.0

    Scored across 15 tools

    Disambiguation4/5

    Most tools have clearly distinct roles: stage lifecycle, act/capture/wait, annotation lifecycle, measurement, scenario runs, and diffing. There is minor overlap between act and scenario_run for executing steps, and between stage_state and measure for error reporting, but descriptions clarify the different scopes.

    Naming Consistency3/5

    Prefixes like stage_* and annotations_* help group related tools, but conventions are mixed: noun_verb (stage_open, annotations_get), verb_noun (annotate_start), and bare verbs (act, capture, diff, measure). The names remain readable but are not predictable throughout.

    Tool Count5/5

    Fifteen tools map cleanly to distinct QA capabilities—browser staging, interaction, capture, waiting, annotations, findings, measurement, scenario runs, and diffing. There is no obvious filler, and the count fits the server's apparent scope.

    Completeness4/5

    The core QA loop is covered: open/focus/close a stage, act, capture, wait, measure, run scenarios, diff, annotate, and store findings. However diff references a promoted baseline with no visible baseline promotion/management tool, and findings_store has no retrieval counterpart, leaving some workflow gaps.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources