Skip to main content
Glama
AndreXes03

ae-agent-lab-demo

by AndreXes03
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Render frame

ae_render_frame

Render After Effects frames to PNG for visual verification of edits, motion checks, and numeric detection of black bars, letterboxing, and content bounds.

Instructions

Render one or more frames to PNG. Use to visually verify edits. The agent's 'eyes' — pair with mutations for a visual feedback loop. Experimental preview requests half or quarter resolution for up to 6 frames; inspect returned dimensions and warnings. Headless and deterministic. Pass time for one frame, or times for several in ONE call (motion checks): files land at _.png and are listed in frames. contactSheet tiles every frame into one labelled PNG (_sheet.png) so a motion check is one image; analyze measures each capture (uniform edge bands = black bars / transparent margins, content bounds, coverage) so off-frame elements and letterboxing are caught numerically. In color-managed projects (workingSpace != None) the capture applies AE's own display transform via a transient OCIO Display Transform adjustment layer, and the PNG comes back viewer-accurate and sRGB-tagged. Where that layer cannot be used — read-only mode, an AE without the OCIO effect, or a failed capture calibration — the result falls back to a pure-math ACES conversion or to raw values with an explicit colorWarning; check colorPipeline / colorWarning on the response.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
timeNoTime in seconds to render. Give exactly one of `time` or `times`.
timesNoSeveral times in seconds, rendered in ONE call. Files are written as <outPath stem>_<index><ext> and reported in `frames` (index-aligned).
analyzeNoMeasure each capture: uniform bands at every edge (width + transparent/color — black bars, letterboxing, empty margins), the bounding box of non-background pixels, coverage, mean RGB. Reported per frame as `analysis` (measured on the capture before color conversion).
outPathYesAbsolute path to write the PNG. Parent directory is created if missing. With `times`, used as the naming stem for every frame.
previewNoExperimental preview: temporarily request half or quarter resolution, then restore the setting. AE may return full-size PNGs; check dimensions/previewWarning. This can dirty the project. Use full resolution for fine-detail approval.
instanceNoAfter Effects instance to address for this call, when several are running (AfterFX.exe -m): an instance id (its AE_MCP_INSTANCE at launch, or the `name` given to instance.start) or the name of the project file it has open. Omit to use this server's default (AE_MCP_INSTANCE, else the single live instance). ae_context and ae_do instance.list show what is live.
colorManagedNo'auto' (default): detect the working space and return a viewer-accurate, 8-bit sRGB-tagged PNG. 'off': raw legacy output (16-bit, untagged, working-space values — dark/wrong-looking in color-managed projects).
compNameOrIdYesComposition name or numeric item id.
contactSheetNoTile all rendered frames into ONE labelled PNG (#index + time above each tile). Pass {} for defaults.
useDisplayStartTimeNoIf true, times are interpreted relative to comp.displayStartTime. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0-alpha.3-studio.3

TDQS

A4.6/5.0
Behavior4/5

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

With only destructiveHint=false in annotations, the description carries the behavioral load and does well: it discloses that preview can dirty the project, that AE may ignore the resolution request (check previewWarning), the file naming scheme, the OCIO display-transform mechanism, and the fallback ladder to ACES/raw with colorWarning. It does not cover auth/permissions or instance contention in depth, but the mutation-risk and failure-mode disclosure is notably strong.

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 purpose before the mode-specific detail, and each sentence covers a distinct concern (motion, contact sheet, analysis, color). It is dense and long for one tool, with some overlapping statements about warnings, but little is pure filler.

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?

No output schema exists, yet the description names the return surface the agent must read (frames, analysis, colorPipeline, colorWarning, previewWarning) and explains the color-managed fallback chain. For a 10-param tool with nested objects and no output schema, this is complete enough to call and interpret correctly.

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, but the description adds real meaning beyond the schema: it specifies the <outPath stem>_<index>.png landing convention, that frames are index-aligned in `frames`, and that analyze acts on the capture before color conversion. Those are semantic relationships not encoded in the property descriptions.

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?

Opens with a specific verb+resource+output format ('Render one or more frames to PNG') and immediately frames the role ('the agent's eyes ... pair with mutations'), which cleanly separates it from planning/save/inspect siblings. An agent knows exactly what this produces versus ae_comp_info or ae_do.

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?

Explicit when-to-use ('Use to visually verify edits'), a clear routing rule for time vs times, and prescriptive guidance for each mode: contactSheet for one-image motion checks, analyze for numeric off-frame detection, full resolution for fine-detail approval, and preview only as an experimental path. Alternatives and exclusions (preview can dirty the project) are stated, not inferred.

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