Skip to main content
Glama
Sign In
adb-ai

adb-ai

by cyberpunk2183
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

adb_mirror

Open a live scrcpy window of the Android device screen so a human can watch the agent's actions and take over with mouse and keyboard; optionally record the session to MP4.

Instructions

Open a live window of the device's screen on the operator's computer, using scrcpy, so a human can watch what you are doing and take over with mouse and keyboard. It is for them, not for you: you cannot see the window, so keep using adb_screenshot to look at the screen. Needs scrcpy installed and a desktop session; it does not work from Termux.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNodefault start
deviceNoserial, ip[:port] or saved alias; omit to use the default device
recordNoalso save the session to this .mp4 path - say so before you do it
max_sizeNolimit the longest side in pixels, e.g. 1024 on a slow network
view_onlyNoshow the screen without giving mouse and keyboard control

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses that the agent gains no visual feedback from this call, that external software (scrcpy) and a graphical session are required, and that Termux environments fail. It adds a warning to announce recording before starting. It does not describe lifecycle behavior such as what start does if a session already exists, or what status returns, which keeps it short of a 5.

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

Conciseness5/5

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

Three tight sentences, front-loaded with what the tool does and immediately followed by the crucial caveat that the agent is blind to it. Every sentence carries information the structured fields do not.

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

Completeness4/5

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

For a 5-parameter tool with no annotations and no output schema, the description covers purpose, audience, prerequisites, and failure environment. The gap is the action lifecycle: nothing tells the agent when to use stop or status versus start, which matters for a stateful session tool.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, and the description goes beyond it by explaining the human-control implication behind view_only and by putting a social constraint on record ('say so before you do it'). The action enum (start/stop/status) is never discussed in the description, so the extra value is real but partial.

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

Purpose5/5

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

States a concrete verb and resource: open a live window of the device's screen on the operator's computer using scrcpy, with mouse/keyboard takeover. It also explicitly separates itself from the nearest sibling by saying the agent cannot see the window and should keep using adb_screenshot. An agent can identify the tool without opening the schema.

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

Usage Guidelines5/5

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

Gives an explicit when-to-use ('so a human can watch what you are doing and take over'), an explicit when-not ('It is for them, not for you... keep using adb_screenshot'), and names the alternative. It also states preconditions (scrcpy installed, desktop session) and an environment exclusion (does not work from Termux).

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