Skip to main content
Glama
callstack

agent-device

Official
by callstack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Related Servers

Alternatives to agent-device

No user-submitted related servers found.

    Related Servers

    • Taproom

      batteryshark
      A
      license
      Not graded
      quality
      D
      maintenance
      Discovers and manages portable agent capabilities (skills and MCP servers) from configurable collections, providing search, inspection, and local installation via CLI and MCP tools.
      1
      MIT

    • antigravity-mcp

      alvarosw
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP-compatible coding agents to run the local Antigravity CLI as a coding agent, manage conversation context and common options, and inspect usage, quota, models, version, help, and read-only slash commands.
      25 npm
      MIT

    • jwx-mcp

      JustworxCloud
      F
      license
      A
      quality
      C
      maintenance
      Exposes Justworx devices to AI agents as MCP tools and resources, backed by the public Developer API. Supports local stdio and hosted remote OAuth operation for controlling device IO, rules, and viewing live state.
      6
      -

    • mcp-bridge

      ctrlpi
      A
      license
      A
      quality
      C
      maintenance
      Enables an AI agent to control one or more remote GPIO agents through a conversation by proxying tool calls to their REST APIs. It supports API-key authentication, LAN discovery, and both stdio and Streamable HTTP transports.
      14
      1
      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

    C2.9/5.0

    Scored across 59 tools

    Disambiguation2/5

    Several tool pairs have heavily overlapping purposes: gesture/swipe, find vs get/is (searching and reading UI), session vs events, batch vs replay, logs vs trace vs perf vs network. Descriptions are detailed but an agent must read carefully to distinguish e.g. get versus find or click versus press versus longpress, and scroll versus swipe.

    Naming Consistency2/5

    Mixed conventions: mostly bare verbs (get, is, click, press, type, fill, boot), some hyphenated compounds (longpress is one word, install-from-source, action-button, app-switcher, install-from-source, trigger-app-event), some nouns (logs, network, screenshot, snapshot, events, artifacts, settings, capabilities), and odd ones (metro, fold, is, appstate). No predictable verb_noun pattern.

    Tool Count1/5

    59 tools is extreme for a device automation server, far beyond the typical 3-15 range; the surface spans gestures, device lifecycle, apps, logging, profiling, recording, web, TV, and diagnostics, making selection error-prone and maintenance heavy.

    Completeness4/5

    Coverage is very broad: device/emulator lifecycle (boot, shutdown, install, reinstall), app control (open, close, apps, app-switcher), full interaction set (click, press, longpress, fill, type, swipe, gesture, scroll), observability (snapshot, screenshot, logs, network, perf, trace, record), and platform extras (tv-remote, fold, clipboard, alerts). Minor gaps like no explicit uninstall or delete-artifact—but most workflows are covered.

    Maintenance

    ActivityActive
    ResponsivenessResponsive

    Resources