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/unbounce/agent-pluginsWrote 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/unbounce/agent-plugins/unbounce-mcp)<a href="https://agentmods.dev/plugins/unbounce/agent-plugins/unbounce-mcp"><img src="https://agentmods.dev/badge/plugins/unbounce/agent-plugins/unbounce-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/unbounce/agent-plugins/unbounce-mcp"><img src="https://agentmods.dev/badge/plugins/unbounce/agent-plugins/unbounce-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
unbounce-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 3d 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": "unbounce-mcp",
"version": "1.0.417",
"description": "Author and manage Unbounce landing pages through Unbounce MCP.",
"author": {
"name": "Unbounce"
},
"license": "MIT"
}
What it installs
The manifest is a name and a version. 4 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 580 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.
- 3d ago Changed 09dcb58e71c6
- 5d ago Changed 8301e00a8f2a
- 16d ago Changed 969374c155be
- 17d ago Changed 1f793894c81f
- 19d ago Changed 52691cacf5dc
- 22d ago Changed a6acd16f2e26
- 24d ago Changed 4b403966b05e
- 25d ago Changed 7d0c1a405f89
- 29d ago Changed e80698fe554f
- 1mo ago First seen · 10 lines scan A 30509df68036
unbounce-mcp is a plugin published in the GitHub repository unbounce/agent-plugins (2 stars, last pushed 5d 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 2026-08-31.
unbounce-mcp compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unbounce-mcpunbounce/agent-plugins | Plugin | 2 | 5d ago | MIT | A | — | Claude Code |
| whimsicalWhimsicalCode/mcp-server-guide | Plugin | 11 | 24d ago | MIT | A | — | Claude Code |
| canvas-to-codeopensesh/canvas-to-code | Plugin | 6 | 26d ago | MIT | A | — | Claude Code |
| creativenatthasath/natthasath-marketplace | Plugin | 1 | 10d ago | MIT | A | — | Claude Code |
| multaialo-exp/multai | Plugin | 4 | 25d ago | none | A | — | Claude Code |
| wp-ux-design-claude-skillxonack/wp-ux-design-claude-skill | Plugin | 7 | 9mo ago | MIT | A | — | Claude Code |
| pencil-atelierJesusJimenezC/pencil-atelier | Plugin | 7 | 6mo ago | GPL-3.0 | A | — | Claude Code |