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/growilabs/growi-mcp-serverWrote 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/growilabs/growi-mcp-server/gemini-extension)<a href="https://agentmods.dev/plugins/growilabs/growi-mcp-server/gemini-extension"><img src="https://agentmods.dev/badge/plugins/growilabs/growi-mcp-server/gemini-extension/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/growilabs/growi-mcp-server/gemini-extension"><img src="https://agentmods.dev/badge/plugins/growilabs/growi-mcp-server/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
growi-mcp-server 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 10d 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": "growi-mcp-server",
"version": "1.8.0",
"description": "MCP server that connects AI models to GROWI wiki content. Enables searching, reading, and creating pages in your GROWI knowledge base.",
"settings": [
{
"name": "Default App Name",
"description": "The default GROWI app name to use",
"envVar": "GROWI_DEFAULT_APP_NAME"
},
{
"name": "App Name",
"description": "Name identifier for the GROWI app",
"envVar": "GROWI_APP_NAME_1"
},
{
"name": "API Token",
"description": "API token for authenticating with GROWI",
"envVar": "GROWI_API_TOKEN_1",
"sensitive": true
},
{
"name": "Base URL",
"description": "Base URL of the GROWI instance (e.g. https://your-growi.example.com)",
"envVar": "GROWI_BASE_URL_1"
}
],
"// mcpServers.growi.cwd": "The parent of the extension directory is used on purpose: the extension directory itself holds a package.json named @growi/mcp-server, so npx resolves that local package instead of the published one and fails with mcp-server: not found. Leaving cwd out is worse, because npx then runs inside whatever project the user started gemini in: that project's .npmrc decides which registry is used, and its .env files leak GROWI settings into this server.",
"mcpServers": {
"growi": {
"command": "npx",
"args": ["-y", "@growi/[email protected]"],
"cwd": "${extensionPath}${/}.."
}
}
}
What ships with it
4 files beside gemini-extension.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.
- 10d ago First seen · 37 lines scan A 6c878facdd45
growi-mcp-server is a plugin published in the GitHub repository growilabs/growi-mcp-server (20 stars, last pushed 10d 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 2026-10-06.
Other plugins, from other repositories
kordoc-workbench
Analyze Korean HWP/HWPX forms and create deterministic HWPX reports from Markdown. Lightweight core with optional OCR/PDF extensions.
fedramp-ssp
Convert FedRAMP Rev 5 Moderate SSP DOCX templates to validated OSCAL 1.2.0 JSON. Wraps ethanolivertroy/frdocx-to-froscal-ssp — ready for oscal-cli, Compliance Trestle, eMASS, and FedRAMP 20X workflows.
repo-to-content
Convert GitHub repos into polished content (PDF, white paper, internal doc, public-docs publication) via Typst, with optional AI banner generation and multi-target publishing.
collate
A plugin that provides an end-to-end workflow for OCR and proofreading historical Chinese documents. OCR turns scanned page images into editable text.
agentwiki
Drive AgentWiki via CLI and MCP — manage documents, folders, search, knowledge graph, uploads, static sites, sharing.
notion-image
A Notion add-on for uploading image files directly through Notion's File Uploads API. Notion is a workspace for documents, databases, and project information.