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/sandraschi/midasheng-gen-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/sandraschi/midasheng-gen-mcp/midasheng-gen-mcp)<a href="https://agentmods.dev/plugins/sandraschi/midasheng-gen-mcp/midasheng-gen-mcp"><img src="https://agentmods.dev/badge/plugins/sandraschi/midasheng-gen-mcp/midasheng-gen-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/plugins/sandraschi/midasheng-gen-mcp/midasheng-gen-mcp"><img src="https://agentmods.dev/badge/plugins/sandraschi/midasheng-gen-mcp/midasheng-gen-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
midasheng-gen-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 11d 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": "midasheng-gen-mcp",
"version": "0.1.0",
"description": "Unified audio scene generation MCP server",
"hooks": "../hooks/hooks.json"
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 30 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 11d ago First seen · 7 lines scan A bff601b6cab8
midasheng-gen-mcp is a plugin published in the GitHub repository sandraschi/midasheng-gen-mcp (1 stars, last pushed 11d ago), licensed Apache-2.0. 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 2026-08-31.
Other plugins, from other repositories
inkscape-mcp
Inkscape MCP server for SVG and vector graphics operations.
blender-mcp
Blender 3D automation via MCP.
mcp-tts
Text-to-Speech skills for automatic announcements using TTS.
runapi
RunAPI model discovery, pricing lookup, media task creation, polling, and balance checks for Claude Code.
talkthrough
Turn screen recordings into transcript, exact frames, OCR and wall-clock evidence — then into ready-to-file bug drafts, specs, backlogs and meeting actions. Bundles the talkthrough MCP server, six workflow commands, a triage agent, and an agent skill.
claude-music
AI music production suite using ACE-Step 1.5 via direct Python API. Song generation, cover/style transfer, section editing (repaint), track extraction, multi-track layering, audio completion, songwriting, analysis, platform export, enhancement, and LoRA training. 50+ languages, 10-minute compositions, 48kHz stereo.