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/shigechika/gwsadm-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/shigechika/gwsadm-mcp/plugin)<a href="https://agentmods.dev/plugins/shigechika/gwsadm-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/shigechika/gwsadm-mcp/plugin/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/shigechika/gwsadm-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/shigechika/gwsadm-mcp/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gwsadm-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 14d 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "gwsadm-mcp",
"displayName": "gwsadm-mcp",
"description": "Google Workspace security-audit MCP for Claude Code, through a service account with domain-wide delegation. Investigate suspicious/disabled logins, suspended accounts, third-party OAuth grants, Drive external sharing, group delivery policy, and Gmail message tracing across one or more Workspace domains, plus a one-shot daily_brief. Read-only as installed — the one write tool (sign_out_user) exists only when GWSADM_ENABLE_SIGN_OUT=1 is set. Needs a local GWSADM_CONFIG INI file, and the Google Cloud service-account JSON key(s) it references, already present on the machine; the plugin cannot create or supply those files for you.",
"author": {
"name": "AIKAWA Shigechika",
"url": "https://github.com/shigechika"
},
"homepage": "https://shigechika.github.io/gwsadm-mcp/",
"repository": "https://github.com/shigechika/gwsadm-mcp",
"license": "MIT",
"keywords": [
"google-workspace",
"admin-sdk",
"directory",
"gmail",
"drive",
"audit",
"security"
]
}
What it installs
The manifest is a name and a version. 1 MCP server travel with it, and installing the plugin installs all of 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.
- 14d ago Changed 6517bcfb2f55
- 2mo ago First seen · 23 lines scan A 1b7646cfc800
gwsadm-mcp is a plugin published in the GitHub repository shigechika/gwsadm-mcp (0 stars, last pushed 12d 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.
gwsadm-mcp compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gwsadm-mcpshigechika/gwsadm-mcp | Plugin | 0 | 12d ago | MIT | A | — | Claude Code |
| humanizerblader/humanizer | Plugin | 66k | 11d ago | MIT | A | — | Claude Code |
| claude-plugins-official marketplaceanthropics/claude-plugins-official | Plugin | 46k | today | Apache-2.0 | A | — | Claude Code |
| themes-examplegoogle-gemini/gemini-cli | Plugin | 109k | today | Apache-2.0 | A | — | Gemini CLI |
| nextjsvercel/next.js | Plugin | 143k | yesterday | MIT | A | — | Claude Code |
| knowledge-work-plugins marketplaceanthropics/knowledge-work-plugins | Plugin | 35k | yesterday | Apache-2.0 | A | — | Claude Code |
| code-modernizationanthropics/claude-plugins-official | Plugin | 46k | today | Apache-2.0 | A | — | Claude Code |