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/bitovi/cascade-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/bitovi/cascade-mcp/cascade-mcp)<a href="https://agentmods.dev/plugins/bitovi/cascade-mcp/cascade-mcp"><img src="https://agentmods.dev/badge/plugins/bitovi/cascade-mcp/cascade-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/bitovi/cascade-mcp/cascade-mcp"><img src="https://agentmods.dev/badge/plugins/bitovi/cascade-mcp/cascade-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cascade-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 1mo 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": "cascade-mcp",
"description": "Skills for generating design review questions, posting to Figma/Jira, and writing user stories via Cascade MCP",
"author": { "name": "Bitovi" },
"mcpServers": {
"cascade-mcp": {
"type": "http",
"url": "http://localhost:3000/mcp"
}
}
}
What it installs
The manifest is a name and a version. 13 skills travel with it, and installing the plugin installs all of them — 1,012 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cascade-analyze-feature-scope A 111 tokens
- Skill cascade-analyze-figma-frame A 80 tokens
- Skill cascade-analyze-figma-frame-mcp A 90 tokens
- Skill cascade-answer-design-questions-post-to-figma A 55 tokens
- Skill cascade-answer-design-questions-post-to-jira A 59 tokens
- Skill cascade-load-linked-resource-content A 80 tokens
- Skill cascade-post-design-questions-to-figma A 60 tokens
- Skill cascade-summarize-document-content A 58 tokens
- Skill cascade-post-design-questions-to-jira A 64 tokens
- Skill write-next-story-from-shell-story B 97 tokens
- Skill generate-behavior-questions B 62 tokens
- Skill write-jira-story B 102 tokens
- Skill write-shell-stories B 94 tokens
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.
- 1mo ago First seen · 12 lines scan A 463729ac5cd3
cascade-mcp is a plugin published in the GitHub repository bitovi/cascade-mcp (24 stars, last pushed 2mo 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 2026-08-30.
Other plugins, from other repositories
interior-designer
Write project proposals, draft spec sheets, and create client presentations.
design-ops
Design operations toolkit for design companies - dashboard, integrations, and utility commands for team productivity.
product-development-suite
Complete suite for single-person product development: writing, database design, product management, UI/UX design, and solution architecture.
pincushion
View, claim, and resolve stakeholder feedback pins directly in Cursor. Installs the Pincushion MCP server and adds /pins, /my-pins, /resolve, and /feedback-summary slash commands.
uxcel
UX and product management skills from Uxcel lessons — audits, screens, flows, components, deliverables, processes, and workflows. Use for design reviews, heuristics audits, PRDs, roadmaps, onboarding flows, accessibility, and PM discovery.
pm-figma
Figma skills for PMs and designers: Component Audit, Design Brief, Annotation Guide, Design Review, User Flow Planner, Variant Matrix, Spacing System, Prototype Plan, Design QA, PM Design Critique. Work smarter across the full Figma design lifecycle.