Skip to main content
Glama

Related Servers

Alternatives to bad-ass-mcp

No user-submitted related servers found.

    Related Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      An MCP server that gives any AI assistant eyes and hands on your desktop — screenshots, clicking, typing, OCR, window management, accessibility-tree queries, workflow recording.
      5
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      An accessibility-first Windows computer-use MCP server that lets AI agents find and click real UI Automation controls, falling back to a vision model of your choice only when a control isn't exposed. Agents get short text results instead of screenshots while driving the real mouse and keyboard, with a visible control panel and hard stops.
      Apache 2.0
    • A
      license
      A
      quality
      C
      maintenance
      Cross-platform desktop automation MCP server that lets AI agents capture screenshots, run OCR with UI-element classification, control mouse/keyboard, and launch programs on Linux, macOS, and Windows.
      20
      2
      MIT
    • A
      license
      A
      quality
      A
      maintenance
      An open-source MCP server that lets any coding agent operate your computer like a person does—reading the UI through accessibility trees, clicking and typing in the background, showing an agent pointer, zooming into regions, and driving your signed-in Chrome on macOS, Windows, and Linux.
      41
      41
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      An open-source MCP server for macOS and Windows that provides native desktop control via Accessibility APIs, OCR, and Chrome CDP. It enables AI agents to interact with applications, manage browser sessions, and automate workflows with high-speed native UI actions.
      49 npm
      15
      AGPL 3.0

    TDQS

    A3.6/5.0

    Scored across 18 tools

    Disambiguation4/5

    Most tools have a clearly distinct purpose (element click vs coordinate click, element wait vs text wait vs window wait), and descriptions explicitly frame click_at as a fallback for webview/canvas content. A few pairs still require reading descriptions to choose correctly: click vs click_at, find_elements vs get_tree, and run_sequence vs the individual action tools it wraps. learn_layout also overlaps with find_elements as a caching layer.

    Naming Consistency4/5

    Nearly all names follow a snake_case verb_noun pattern (find_elements, wait_for_window, select_option, start_recording). The deviations are single-word names like screenshot, click, and drag, which are still readable and conventional for their actions. No mixed casing or contradictory verb styles.

    Tool Count4/5

    At 18 tools this is slightly above the ideal range, but the domain (desktop GUI automation) genuinely requires windows, elements, input, capture, waits, and batching. Each tool covers a distinct capability, with no filler or redundant variants. Only run_sequence arguably duplicates existing tools, and it earns its place as a round-trip reducer.

    Completeness4/5

    The surface covers discovery (list_windows, get_tree, find_elements), interaction (click, click_at, type_text, select_option, press_key, drag), reading (get_value, wait_for_text), capture (screenshot, recording), and batching. Gaps exist: no dedicated scroll or hover tool (partially mitigated by press_key PageUp/PageDown), and no explicit window focus/move/resize/close or app-launch operation. These are workable but would force agents into indirect approaches.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues