What is mcp-after AGENTS.md?

Repository instructions for installing mcp-after, an MCP server that connects AI clients to Adobe After Effects, a motion-graphics application.

Use them to configure supported AI clients to launch the server, merge settings into existing configuration files, and verify the setup.

They prevent unsafe or incomplete setup by requiring checks for the client, Windows, Node.js, and After Effects while preserving existing configuration.

How leo10m2010/mcp-after configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to leo10m2010/mcp-after. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/leo10m2010/mcp-after/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/leo10m2010/mcp-after

Made for: Codex, OpenCode.

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/instructions/leo10m2010/mcp-after/agents-md/github.svg)](https://agentmods.dev/instructions/leo10m2010/mcp-after/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/leo10m2010/mcp-after/agents-md"><img src="https://agentmods.dev/badge/instructions/leo10m2010/mcp-after/agents-md/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/instructions/leo10m2010/mcp-after/agents-md"><img src="https://agentmods.dev/badge/instructions/leo10m2010/mcp-after/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 822 This file is loaded in full into every session.

When invoked 822 The same file — it is already loaded in full.

Security scan B 1 finding. 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	$0.00822	$0.00822
Opus 5.5	$0.00329	$0.00329
Sonnet 5.5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 2mo ago against content hash ba60f7f0e4fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mcp-after AGENTS.md scanned grade B with 1 finding 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

These clients share `~/.codex/config.toml`. The equivalent TOML is in

AGENTS.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for AI agents

This repository is a local Windows MCP server for Adobe After Effects. A user may give an AI only this repository URL and ask it to install the server. Follow these instructions instead of guessing client configuration.

Installation goal

Configure the user's existing MCP client to launch:

npx -y github:leo10m2010/mcp-after

Do not clone the repository unless the user wants to develop the server.

Before changing configuration

Identify the client: OpenCode, Claude Desktop, Claude Code, ChatGPT Desktop with Codex, Codex CLI, Codex IDE, Cursor, or ChatGPT web.
Confirm the operating system is Windows.
Confirm node --version is 20 or newer and npx --version succeeds.
Confirm Adobe After Effects is installed.
Preserve every unrelated field and MCP server in the user's config.
Never overwrite a complete config file with a minimal example.

Client-specific setup

OpenCode

Merge examples/opencode.json into the user's existing opencode.json. Keep $schema. The MCP command must be an array. Restart OpenCode and run opencode mcp list.

Claude Desktop on Windows

Use Settings > Developer > Edit Config, or edit %APPDATA%\Claude\claude_desktop_config.json. Merge the entry from examples/claude-desktop.json under mcpServers. Fully quit and restart Claude Desktop, then inspect Connectors > Manage connectors.

Claude Code

Run:

claude mcp add --scope user --transport stdio after-effects -- npx -y github:leo10m2010/mcp-after
claude mcp list

ChatGPT Desktop with Codex, Codex CLI, or Codex IDE

Run:

codex mcp add after-effects -- npx -y github:leo10m2010/mcp-after
codex mcp list

These clients share ~/.codex/config.toml. The equivalent TOML is in examples/codex.toml. Restart the desktop app or IDE extension after editing.

Cursor

Merge examples/cursor.json into .cursor/mcp.json, then restart Cursor.

ChatGPT web

Do not claim that ChatGPT web can launch this local stdio process. It only uses remote MCP-backed apps. Recommend ChatGPT Desktop with Codex or Codex CLI for local After Effects. Do not expose this MCP through a public tunnel: the after_effects_run_jsx tool can execute code and access local files.

Read the full file on GitHub · 99 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.

2mo ago First seen · 99 lines · 822 tokens per session scan B ba60f7f0e4fe

Subscribe to this mod's changes

mcp-after AGENTS.md is an instructions file published in the GitHub repository leo10m2010/mcp-after (0 stars, last pushed 4mo ago), licensed MIT. It adds 822 tokens to every session, about $0.0033 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

mcp-after AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-after AGENTS.mdleo10m2010/mcp-after	Instructions file	0	4mo ago	MIT	B	822	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-after: Instructions file for Codex