agent-device
OfficialRelated Servers
Alternatives to agent-device
No user-submitted related servers found.
Related Servers
- FlicenseAqualityBmaintenanceActs as a personal AI development environment manager, enabling workspace bootstrapping, headless skill and bundle installation, global caching, and health diagnostics.727 npm-
- AlicenseNot gradedqualityDmaintenanceDiscovers and manages portable agent capabilities (skills and MCP servers) from configurable collections, providing search, inspection, and local installation via CLI and MCP tools.1MIT
- AlicenseNot gradedqualityFmaintenanceActs as a unified dispatch hub for local coding agent CLIs, supporting capability-based routing, schema validation, and retries via MCP tools.MIT
- AlicenseNot gradedqualityDmaintenanceEnables 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.MIT
- FlicenseAqualityCmaintenanceExposes 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-
- AlicenseAqualityBmaintenanceEnables agent hosts to query service status and help, with future tools intended for CIF-based crystal inspection, planning, and execution of deterministic lattice-energy and validation workflows.6MIT
TDQS
Scored across 63 tools
Several core interaction tools have unclear boundaries: click, press, find, and gesture's tap/drag all target and activate UI elements, while scroll, swipe, and gesture overlap for movement. The descriptions are detailed but do not clearly explain when an agent should choose click versus press versus find for the same ref/selector target.
Names consistently use lowercase kebab-case rather than mixing camelCase and snake_case, so they are readable. However, the naming pattern mixes verbs, nouns, and generic terms such as get, is, back, and snapshot, so there is no predictable action-resource convention.
With 63 tools, the surface is far beyond a well-scoped automation toolset and likely overwhelms tool selection. The domain is broad, but many tools are niche variants or overlapping interaction/observation commands that do not each need a separate top-level tool.
The tool set covers device lifecycle, app install/open/close/uninstall, UI interaction, snapshots, screenshots, waits, logs, network, tracing, performance, media, TV, foldables, and replay/test workflows. For mobile and device automation, this is an unusually complete lifecycle surface with no obvious core gap.