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.
git clone --depth 1 https://github.com/JUNKDOGE-JOE/after-effects-mcpWrote 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.
[](https://agentmods.dev/mcp/junkdoge-joe/after-effects-mcp/ae-mcp)<a href="https://agentmods.dev/mcp/junkdoge-joe/after-effects-mcp/ae-mcp"><img src="https://agentmods.dev/badge/mcp/junkdoge-joe/after-effects-mcp/ae-mcp/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.
<a href="https://agentmods.dev/mcp/junkdoge-joe/after-effects-mcp/ae-mcp"><img src="https://agentmods.dev/badge/mcp/junkdoge-joe/after-effects-mcp/ae-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ae-mcp 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.
What it actually says
{
"ae-mcp": {
"command": "npx",
"args": [
"-y",
"ae-mcp-jkdg"
],
"env": {}
}
}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 · 10 lines scan A 2ff4042d1aee
ae-mcp is an MCP server published in the GitHub repository JUNKDOGE-JOE/after-effects-mcp (58 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-30.
Other mcp servers, from other repositories
premiere-pro
MCP server for Adobe Premiere Pro with 321 core AI video editing tools and a capability-aware UXP bridge for supported Premiere workflows. Runs locally from the premiere-pro-mcp npm package.
photoshop-beta-control
MCP server "photoshop-beta-control" as configured in kiki348/photoshop-beta-control. Runs ./scripts/mcp_server.py with python.
adobe-mcp
Drive Adobe CC (AE, Photoshop, Illustrator, Premiere, Character Animator) from any MCP client. Runs locally from the @ajsmonty/adobe-mcp npm package. Needs 1 environment variable to run.
premierpro-mcp
MCP server "premierpro-mcp" as configured in ayushozha/AdobePremiereProMCP. Launched with ./go-orchestrator/bin/premierpro-mcp --log-level error.
speak-aloud
MCP server "speak-aloud" as configured in tsuru0805/speak-aloud-mcp. Launched with speak-aloud-mcp. Needs 4 environment variables to run.
sticker-mcp
MCP server "sticker-mcp" as configured in asashiki/sticker-mcp. Runs locally from the @asashiki/sticker-mcp npm package.