Skip to main content
Glama
linux-computer-use-mcp

linux-computer-use-mcp

by dhakseshr

batch

Run multiple desktop actions in one call—such as clicking, typing, and pressing keys—then return a screenshot. Use it to execute known multi-step UI sequences faster than separate calls.

Instructions

Run several actions in ONE call (much faster than one call per action), then return a screenshot. Use it whenever you already know the next few steps, e.g. click a field, type, press Enter.

Each action is an object with an "action" key plus that action's arguments: {"action": "click", "x": 100, "y": 200, "button": "left", "clicks": 1, "modifiers": ["ctrl"]} {"action": "move", "x": 100, "y": 200} {"action": "drag", "start_x": 1, "start_y": 2, "end_x": 3, "end_y": 4} {"action": "scroll", "direction": "down", "amount": 5, "x": 640, "y": 400} {"action": "type", "text": "hello"} {"action": "key", "keys": "ctrl+l", "repeat": 1} {"action": "hold_key", "keys": "shift", "seconds": 1} {"action": "wait", "seconds": 3} (returns early once the screen settles) {"action": "open_application", "name": "Google Chrome"} {"action": "focus_window", "query": "WhatsApp"} Coordinates refer to the most recent screenshot. Between steps that can change the UI (clicks, keys, scrolls) the screen is briefly allowed to settle. Stops at the first failing step.

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": {
      "actions": "<actions>"
    },
    "name": "batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionsYes
screenshotNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that the screen settles between UI-changing steps, execution stops at the first failing step, coordinates are relative to the most recent screenshot, and that wait may return early. What is missing is failure semantics — whether partial actions persist, how the failing step is reported, and whether a screenshot is still returned on error.

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?

Front-loaded with purpose and speed rationale, then a scannable example-per-line catalog, then a short block of shared execution semantics. Length is justified by the absence of any schema descriptions; no sentence merely repeats the name or annotations.

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 complex, unannotated tool with no output schema, the description covers the return value (screenshot), cross-step timing, coordinate reference frame, and early termination. It stops short of describing error payloads, per-step results, or whether a failed batch leaves the UI partially mutated — meaningful omissions for a multi-action executor.

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 description coverage is 0%, so the description must compensate, and it does: it enumerates ten action shapes with full field examples and explains that coordinates map to the latest screenshot. The one gap is the 'screenshot' boolean parameter, which is only obliquely implied by 'then return a screenshot' — it never says the flag can be set to false to skip the capture.

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 specific verb and resource ('Run several actions in ONE call... then return a screenshot') and explicitly contrasts with the per-action siblings ('much faster than one call per action'), which are literally present in the sibling list (click, type_text, scroll, etc.). An agent can immediately tell this is the batching counterpart to the single-action tools.

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?

Gives a concrete selection rule: 'Use it whenever you already know the next few steps, e.g. click a field, type, press Enter', which implies batching is for pre-planned sequences and singles are for exploratory steps. It never states an explicit exclusion (e.g. do not batch when each step's target depends on the previous result), so the boundary is clear but not fully fenced.

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