Skip to main content
Glama
Mobile Next MCP Server

Mobile Next MCP Server

Official
by mobile-next

Batch Commands

mobile_batch_commands
Destructive

Run multiple mobile automation steps in one call to fill forms or complete multi-step flows without repeated round-trips; apply one device to every step or override it per step.

Instructions

Run multiple tools in sequence in a single call, e.g. click, type, click, type. Use this to fill forms or perform multi-step flows without round-trips. The device argument is applied to every step unless a step provides its own. Tools allowed as steps: get_more_tools, mobile_list_available_devices, mobile_login_to_cloud_provider, mobile_list_remote_devices, mobile_allocate_remote_device, mobile_release_remote_device, mobile_list_apps, mobile_get_foreground_app, mobile_launch_app, mobile_terminate_app, mobile_clear_app_data, mobile_install_app, mobile_uninstall_app, mobile_get_screen_size, mobile_click_on_screen_at_coordinates, mobile_double_tap_on_screen, mobile_drag_on_screen, mobile_long_press_on_screen_at_coordinates, mobile_list_elements_on_screen, mobile_press_button, mobile_open_url, mobile_swipe_on_screen, mobile_type_keys, mobile_save_screenshot, mobile_take_screenshot, mobile_set_orientation, mobile_fold_device, mobile_set_location, mobile_clipboard, mobile_get_device_logs, mobile_get_orientation, mobile_start_screen_recording, mobile_stop_screen_recording, mobile_list_crashes, mobile_get_crash. A step named "delay" with arguments {"milliseconds": N} (up to 10000) waits before the next step, e.g. for an animation or a page load to finish before looking at the screen.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "device": "<device>",
      "steps": "<steps>"
    },
    "name": "mobile_batch_commands"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsYesTools to run, in order
deviceYesThe device identifier to use. Use mobile_list_available_devices to find which devices are available to you.
stopOnErrorNoStop at the first failing step. Defaults to true
listElementsAtEndNoRun mobile_list_elements_on_screen after the last step and include its result. Defaults to false

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.18
    • changedInput schema / properties / steps / items / properties / name / description
      Previous value: -"Name of a tool allowed as a step, e.g. mobile_click_on_screen_at_coordinates"New value: +"Name of a tool allowed as a step, e.g. mobile_click_on_screen_at_coordinates, or \"delay\""
  2. Changed1 schema field changedv1.0.11
    • changedInput schema / properties / steps / items / properties / name / description
      Previous value: -"Tool name, e.g. mobile_click_on_screen_at_coordinates"New value: +"Name of a tool allowed as a step, e.g. mobile_click_on_screen_at_coordinates"
  3. Changed1 schema field changedv1.0.6
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  4. Addedv1.0.3

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare openWorldHint and destructiveHint, and the description adds real behavior beyond them: device inheritance to every step unless overridden, the closed set of callable step tools, and a special 'delay' step with a 10000ms cap for waiting on animations or page loads. It does not say how failures propagate across the sequence or what the aggregated result looks like, which matters for a destructive batch wrapper with no output schema.

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?

Purpose and the round-trip rationale are front-loaded, and the device-inheritance rule and delay step follow in a sensible order. The 35-name allowlist is bulky, but it is the actual constraint on valid step values, so it earns its space rather than padding.

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 4-parameter meta-tool with full schema coverage and no output schema, the definition covers what the tool is, which steps are legal, and how the device and delay behave. The notable remaining gap is the shape of the returned per-step results, which an agent needs in order to interpret a batch outcome.

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 the baseline is 3, but the description adds semantics the schema does not: the device argument cascades to every step unless a step supplies its own, and 'delay' is a valid pseudo-step with a milliseconds budget. stopOnError and listElementsAtEnd are left entirely to their schema descriptions, which is acceptable given full coverage.

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?

The first sentence gives a specific verb and resource ('Run multiple tools in sequence in a single call') and immediately disambiguates it from the individual siblings by framing it as a batching layer, reinforced by the explicit allowlist of steps. An agent can tell this is a meta-tool wrapping the single-action tools 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 Guidelines4/5

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

'Use this to fill forms or perform multi-step flows without round-trips' gives a clear positive condition tied to the round-trip cost of chaining single calls. It stops short of stating when NOT to use it (e.g. when intermediate results must be inspected or a step depends on a prior step's output), so the exclusion side is left to inference.

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