Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
quest_devicesA

List connected Quest/Android devices with connection state.

Returns serial, model, connection state (device/unauthorized/offline), and whether the connection is wireless. Use this first if unsure what is connected.

quest_infoC

Get detailed device info: model, OS/firmware version, battery level and temperature, free storage, WiFi IP address, thermal status.

quest_screenshotA

Take a screenshot of what's currently displayed in the headset and return the image so it can be viewed. Auto-wakes the display if the headset is asleep. Optionally saves to save_path (PNG).

quest_installA

Install (sideload) an APK onto the headset. Replaces an existing install of the same package (upgrade). Set grant_permissions=True to auto-grant all runtime permissions (useful for test builds).

quest_uninstallB

Uninstall an app from the headset by package name.

quest_launchB

Launch an app on the headset by package name (e.g. com.mycompany.mygame).

quest_stopB

Force-stop a running app on the headset.

quest_app_listA

List installed apps. filter: 'sideloaded' (default — dev/third-party apps), 'system', or 'all'.

quest_app_infoA

Get app details: version, install/update dates, target SDK, permissions, data size on disk.

quest_clear_dataA

Clear an app's data — resets it to freshly-installed state. Useful for wiping test state (saves, settings, caches).

quest_logsA

Get recent logcat entries as structured logs (timestamp/level/tag/ message). level: V/D/I/W/E/F (minimum severity, default W). tag scopes to one log tag (e.g. 'Unity' or 'VrApi'). pattern is a case-insensitive regex applied to tag+message.

quest_logs_streamA

Watch logs in real time for duration_seconds (max 60) and return everything captured. Use while reproducing a bug: start this, interact with the app, and the tool returns what was logged in that window.

quest_crash_logsA

Get crash and ANR reports (Java crashes, native crashes, ANRs) from the system dropbox, most recent first. Filter by package_name to see crashes for one app. Each entry includes the full stack trace.

quest_performanceC

Get a performance snapshot: CPU usage, memory, thermal status with throttling risk, battery level/drain (mA, negative = discharging), foreground app, and top processes by CPU.

quest_monitorA

Monitor performance over time (max 120s) and return a timeseries of snapshots. Use while exercising an app to spot CPU spikes, memory growth, or thermal climb.

quest_thermalA

Check thermal state: overall throttle status, every temperature sensor with warning/critical flags, and max skin temperature. Quest throttles CPU/GPU as skin temps climb — watch for warnings during long play sessions.

quest_frame_timingA

Get live VR frame timing for the running app: FPS vs target, stale frames, GPU/CPU utilization and dynamic levels, app GPU time vs frame budget. Captures ~6s of the VrApi metrics stream. Falls back to gfxinfo for 2D/panel apps that don't render in VR.

quest_perf_sessionA

Record a full performance profiling session (max 300s) and return a summary, a bottleneck diagnosis (GPU-bound / CPU-bound / thermal throttling / memory pressure / hitching, with evidence and recommendations), and notable events. Use while the user exercises their app in the headset. The full session (per-second VrApi metrics, memory anatomy, thermal timeline) is saved to a JSON file whose path is returned — pass two such paths to quest_perf_diff to compare runs. Defaults to the current foreground app.

quest_perf_diffA

Compare two recorded perf sessions (JSON files from quest_perf_session), e.g. before/after an optimization. Returns metric deltas (fps, stale frames, GPU/CPU load, memory growth) and the verdict change.

quest_launch_benchmarkA

Benchmark an app's cold-start time: force-stop then timed launch, N times (max 5). Returns per-run timings and min/median/max — useful for measuring startup optimizations.

quest_traceA

Capture a perfetto system trace (max 60s): per-thread scheduling, CPU frequencies, graphics events. Use when session metrics show a problem (hitches, CPU-bound) and you need to see exactly what blocked. The .pftrace file can be opened at https://ui.perfetto.dev.

quest_app_memoryA

Get an app's memory anatomy (PSS in KB): java heap, native heap, code, stack, and graphics — graphics allocations (textures, buffers, surfaces) are usually what exhausts memory in VR apps.

quest_screen_recordA

Record the headset screen for N seconds (max 180) and save the MP4 locally. Returns the file path — useful for capturing a bug repro.

quest_pushA

Push a local file to the device (e.g. test assets to /sdcard/Android/data//files/).

quest_pullA

Pull a file from the device to the local filesystem (e.g. save files, logs written by the app).

quest_filesA

List a directory on the device. App data lives under /sdcard/Android/data//files/.

quest_connect_wirelessA

Switch the USB-connected headset to wireless ADB so the cable can be unplugged. The headset must be on WiFi.

quest_set_refresh_rateA

Set the display refresh rate hint (Quest 3: 72/80/90/120 Hz). Apps that request an explicit rate override this.

quest_trackingB

Check tracking subsystem status: head/hand/eye/body/controller tracking service availability, plus guardian boundary state if exposed.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/chisomobanzi/visor'

If you have feedback or need assistance with the MCP directory API, please join our Discord server