o3de-mcp

Overview Schema Source Related Servers Discussions Admin

capture_viewport

Save a screenshot of the rendered O3DE editor viewport to an image file for inspecting or sharing the current level view.

Instructions

Capture a screenshot of the editor viewport.

Captures the rendered frame with Atom's FrameCaptureRequestBus.CaptureScreenshot, then waits on the client for a new, fully written file (O3DE_CAPTURE_WAIT, default 15 s). A level must be open: without one the engine accepts the capture and never writes a file, which is reported as capture_not_written. A PySide6 widget grab is tried first, but it cannot run in the editor's embedded interpreter on O3DE 26.10.0 (QApplication.instance() is None).

Args: output_path: File path for the screenshot (.png, .jpg, .jpeg, .bmp, or .tga). width: Scale width for the PySide6 grab only; ignored by the Atom capture, so it has no effect on 26.10.0. height: Scale height for the PySide6 grab only; ignored like width.

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": {
      "output_path": "<output_path>"
    },
    "name": "capture_viewport"
  }
}

Input Schema

Name	Required	Description	Default
`width`	No
`height`	No
`output_path`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Sep 5, 2026

TDQS

A4.3/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it explains the Atom capture path, the wait/timeout semantics (O3DE_CAPTURE_WAIT, default 15 s), the silent-failure mode reported as capture_not_written, and the PySide6 fallback that cannot run under 26.10.0. Latency, side effect (file write), and environment caveats are all disclosed.

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?

Front-loaded with a one-line summary, then mechanism, caveats, and a clean Args block. It is fairly long and the PySide6 explanation is repeated between the prose and the two scale args, but nearly every sentence carries actionable detail.

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

Completeness5/5

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

An output schema exists, so return values need not be described, and for a tool with zero annotation coverage the description covers preconditions, timeout configuration, failure reporting, and platform limitations. Nothing needed to call it correctly is missing.

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

Parameters5/5

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: output_path is documented with accepted extensions, and width/height are explicitly flagged as no-ops on 26.10.0 ('ignored by the Atom capture'). This meaning exists nowhere in the schema and prevents the agent from relying on width/height.

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: 'Capture a screenshot of the editor viewport.' An agent immediately knows this produces an image. However, it never distinguishes itself from the related siblings capture_renderdoc_frame and get_scene_snapshot, so it stops short of the sibling-aware 5.

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?

It gives an important precondition ('A level must be open') and its failure consequence, which is real usage context. But it never says when to prefer this over capture_renderdoc_frame or get_scene_snapshot, so the when-to-use guidance is only implied.

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

Deploy Server