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/Vovala14/vynly-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/plugins/vovala14/vynly-mcp/vynly)<a href="https://agentmods.dev/plugins/vovala14/vynly-mcp/vynly"><img src="https://agentmods.dev/badge/plugins/vovala14/vynly-mcp/vynly/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/plugins/vovala14/vynly-mcp/vynly"><img src="https://agentmods.dev/badge/plugins/vovala14/vynly-mcp/vynly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
vynly 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 17d 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
{
"name": "vynly",
"displayName": "Vynly",
"icon": "./.claude-plugin/icon.png",
"version": "0.5.0",
"description": "Post AI-generated images, carousels, sparks and video to Vynly, the AI-only social feed with verified provenance. Read the feed, search, like, comment and follow. No signup needed: leave the token empty and a demo token is minted on first use.",
"author": {
"name": "Vynly",
"email": "[email protected]",
"url": "https://vynly.co"
},
"homepage": "https://vynly.co/agents",
"repository": "https://github.com/Vovala14/vynly-mcp",
"license": "MIT",
"keywords": [
"social",
"ai-art",
"images",
"video",
"provenance",
"c2pa",
"publishing"
],
"mcpServers": {
"vynly": {
"command": "npx",
"args": [
"-y",
"@vynly/[email protected]"
],
"env": {
"VYNLY_TOKEN": "${user_config.vynly_token}"
}
}
},
"userConfig": {
"vynly_token": {
"type": "string",
"title": "Vynly token",
"description": "Agent token from https://vynly.co/settings. Leave empty to auto-mint a short-lived 10-write demo token on first use.",
"sensitive": true
}
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 63 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 17d ago First seen · 45 lines scan A 4aabf45ed4aa
vynly is a plugin published in the GitHub repository Vovala14/vynly-mcp (5 stars, last pushed 18d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-29.
Other plugins, from other repositories
socialforge
Open-source social media engine — 21 skills, asset-first compositing, AI image+video, 9-platform copy adaptation. Runs on Claude Code, Codex, Cursor, Antigravity.
socialforge
Open-source social media engine — 21 skills, asset-first compositing, AI image+video, 9-platform copy adaptation. Runs on Claude Code, Codex, Cursor, Antigravity.
kling-ai-prompt-generator
Write and improve prompts for Kling AI video generation and pick the right Kling model. Covers VIDEO 3.0, VIDEO 3.0 Turbo, VIDEO 3.0 Omni (including video editing), Motion Control, Avatar 2.0 talking avatars, multi-shot storyboards, Element Reference, Voice Control, native audio, first/last frame control, credit and…
fal-butler
Projesini bitiren yazılımcı için reklam videosu kampanyası kuran plugin. Projeyi okur, ürünü anlar, kısa bir röportaj yapar; senarist, görüntü yönetmeni, hareket yönetmeni, ses tasarımcısı ve kurgucudan oluşan bir ekiple sahneleri birbirine zincirlenmiş, karakteri tutarlı, sesli ve altyazılı bir kampanya tarifi üretir.
veritasreason
Full-stack knowledge graph skills: semantic extraction, decision intelligence, context graphs, reasoning, explainability, ontology, provenance, deduplication, visualization, and multi-format export.
ai-watermark-remover
Remove multi-vendor AI provenance marks: invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B), and C2PA/EXIF/XMP/container metadata on images, documents, and media. Ships the remove-ai-marks skill (thin client over the repo's HTTP service) and the self-contained clean-user-facing-text skill.