What is add-ae-mcp-tool?

A development procedure for adding tools to a LayerCake MCP integration, which lets an AI assistant access structured project data. It covers deciding the tool type, updating its contract, adding source code, and wiring it into the server.

Adding After Effects inventory tools, exposing compositions, sources, or folders, updating OpenSpec behavior definitions, building ExtendScript entries, and connecting TypeScript loaders.

It provides a repeatable way to add read-only inventory tools while preserving shared code, clear errors, and compatibility with the project’s conventions.

add-ae-mcp-tool — Skill for Claude Code and Codex by alphacornutum

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add alphacornutum/layercake --skill add-ae-mcp-tool

Clone the repo

git clone --depth 1 https://github.com/alphacornutum/layercake

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alphacornutum/layercake/add-ae-mcp-tool/github.svg)](https://agentmods.dev/skills/alphacornutum/layercake/add-ae-mcp-tool)

Your own site

<a href="https://agentmods.dev/skills/alphacornutum/layercake/add-ae-mcp-tool"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/add-ae-mcp-tool/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alphacornutum/layercake/add-ae-mcp-tool"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/add-ae-mcp-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 787 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00092	$0.00787
Opus 5	$0.00046	$0.00394
Sonnet 5	$0.00018	$0.00157
Haiku 4.5	$0.00009	$0.00079

Measured 10d ago against content hash 9b342a4e0dc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-ae-mcp-tool scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.ai/src/skills/add-ae-mcp-tool/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add an AE MCP tool

Follow the inventory pattern already used for comps, sources, and folders.

Steps

Decide tool vs eval
- Repeated read-only structure → dedicated ae_list_* (or similar) tool.
- One-off / mutating → document an ae_eval_script recipe; skip a new tool.
OpenSpec (when contract-facing)
- For new/changed agent-facing behavior, create or update an OpenSpec change and specs under openspec/specs/ before or alongside implementation (see openspec-propose / openspec-apply-change).
ExtendScript source
- Add a typed entry under src/ae-scripts/entries/ that exports main(): string (JSON payload). Import shared helpers from src/ae-scripts/shared/ (e.g. inventory) instead of copying folderPlacement / serializeSourceRef.
- Emit via npm run build:ae-scripts; Node loaders use loadAeScript("<entry>") (self-contained). Do not prepend loadAeHelperScript blobs onto entries that already bundle those helpers.
- Require an open project; throw a clear Error if !app.project.
TypeScript orchestration
- Add list-<name>-script.ts that exports loadAeScript("list-<name>") (plus any intentional parameter preamble only).
- Add list-<name>.ts: host.evalScript(SCRIPT, timeoutMs) → parse → optional filter in TS.
- Extend src/inventory/types.ts and parse.ts with strict runtime checks (throw on malformed JSON/shape).
Register MCP tool
- In src/server.ts, registerTool with Zod inputSchema, clear description (id namespaces, read-only vs mutating), and textResult(JSON.stringify(...), isError).
- Map ConfigError / eval failures to isError: true text, matching existing tools.
Tests + docs
- Unit: script contains shared helpers / key probes; parse + filter fixtures in tests/inventory.test.ts.
- Host: extend tests/host.ae.test.ts behind skipIf gates.
- Update docs/mcp-tools.md tool table and any id-join guidance; keep README.md tool/skill pointers accurate if the surface changed.

Read the full file on GitHub · 56 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 56 lines · 92 tokens per session scan A 9b342a4e0dc1

Subscribe to this mod's changes

add-ae-mcp-tool is a skill published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 787 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents adobe-after-effects after-effects automation mcp motion-graphics

hyperframes-motion-graphics

Create short, unnarrated, design-led motion graphics (under 10s) using HyperFrames. Use when the user wants kinetic type, stat/chart hits, logo stings, lower-thirds, animated tweets/headlines, or transparent overlay motion graphics. MP4 or transparent overlay output. Teaches seek-safe keyframe authoring and the 2-3…

oyi77/1ai-skills · 82 tokens

after-effects-scripting

Drive a running After Effects instance directly from the shell to build, edit and render motion graphics — no MCP, plugin or panel required. Use whenever the user wants Claude to work inside After Effects: building animations, title sequences, logo stings, UI/product motion, data visualisations, or fixing an existing…

Maciejdziuba/youtube-skills · 148 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

x-tweet-by-conversation

Collects every tweet in an X (Twitter) conversation thread given a conversation id (root tweet id) — the focal tweet plus all replies, sub-replies, and quote chains — and returns normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, inreplyto mapping, and cursor for pagination. Use…

browser-act/skills · 218 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.