Skip to main content
Glama

adb_mirror_start

Start live screen mirroring for an Android device using scrcpy, with optional windowed or headless mode and local recording.

Instructions

Start live screen mirroring for a device using scrcpy. Requires scrcpy installed and on PATH. Supports windowed (visual) and headless (no display) modes. One session per device.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "adb_mirror_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoDevice serial
maxFpsNoMaximum frame rate (1-120, default 30)
recordNoRecord to a local file path (e.g., 'mirror.mp4')
bitrateNoVideo bitrate (e.g., '4M', '8M', '2M'). AK2 fix: format-validated at schema layer.4M
maxSizeNoMax dimension in pixels (0 = no limit, max 4096)
headlessNoNo-display mode — useful with recording. Omits the scrcpy window.
stayAwakeNoKeep device awake while mirroring
turnScreenOffNoTurn device screen off during mirroring (saves battery)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.6
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed3 schema fields changedv1.1.3
    • removedInput schema / additionalProperties
      Removed value: -false
    • changedInput schema / properties / bitrate / description
      Previous value: -"Video bitrate (e.g., '4M', '8M', '2M')"New value: +"Video bitrate (e.g., '4M', '8M', '2M'). AK2 fix: format-validated at schema layer."
    • addedInput schema / properties / bitrate / pattern
      Added value: +"^\\d+(\\.\\d+)?[KMG]?$"
  3. First observedv1.1.1

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden and discloses only the scrcpy dependency, headless support, and a one-session-per-device limit. It does not say whether the call blocks or returns immediately after launching a background session, how the session is terminated (adb_mirror_stop), or what error behavior occurs if a session already exists — critical for a 'start' tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the core action, then prerequisites and constraints — no filler. The mode sentence slightly overlaps the schema's headless/record fields, which keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter session-launching tool with no annotations and no output schema, the description covers prerequisites and concurrency but omits lifecycle semantics (blocking vs. async, expected response, how to end the session). It is adequate to start the tool but not complete enough to predict its runtime behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all eight parameters are already documented with defaults, ranges, and patterns. The description restates mode/recording concepts already present in the schema (headless, record) without adding format or interaction details, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Start live screen mirroring for a device using scrcpy') and names the underlying mechanism, which distinguishes it from screenshot/screencap siblings. It does not explicitly differentiate from adb_screenrecord_start or reference its lifecycle partners adb_mirror_stop/adb_mirror_status, leaving that inference to the agent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Requires scrcpy installed and on PATH' is a genuinely useful prerequisite, and 'One session per device' signals a constraint. However, there is no explicit when-to-use guidance versus alternatives such as adb_screenrecord_start (file-only capture) or adb_screencap, and no statement of when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools