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/cosmopig/harukibox-agentWrote 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/mcp/cosmopig/harukibox-agent/harukibox)<a href="https://agentmods.dev/mcp/cosmopig/harukibox-agent/harukibox"><img src="https://agentmods.dev/badge/mcp/cosmopig/harukibox-agent/harukibox/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/mcp/cosmopig/harukibox-agent/harukibox"><img src="https://agentmods.dev/badge/mcp/cosmopig/harukibox-agent/harukibox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
harukibox 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 8d 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
{
"harukibox": {
"command": "npx",
"args": [
"-y",
"@harukibox/mcp"
],
"env": {
"HARUKIBOX_TOKEN": "",
"HARUKIBOX_BASE_URL": ""
}
}
}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.
- 8d ago First seen · 13 lines scan A 56a21f6a23c6
harukibox is an MCP server published in the GitHub repository cosmopig/harukibox-agent (0 stars, last pushed 29d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 mcp servers, from other repositories
mcp-odoo
Odoo MCP for AI agents — 41 tools, gated writes, multi-instance. Free hosted product: ERPipe (mcp.erpipe.com). Runs locally from the odoo-mcp Python package. Needs 4 environment variables to run.
hotelbooking-ai
Hotel Booking MCP Server (Global/AI Edition). Runs locally from the @didaai/hotelbooking-ai npm package. Needs 1 environment variable to run.
marketplaces-mcp-ru
MCP servers for Wildberries and Ozon Seller APIs (schema-driven, safety-gated). Runs locally from the marketplaces-mcp-ru Python package. Needs 5 environment variables to run.
ecommerce
Product and category demand trend volume over time, with growth signals. Free key at trendsmcp.ai. Remote server at ecommerce.api.trendsmcp.ai.
churnkey
Read and manage Churnkey cancel flows, retention metrics, and payment recovery. Remote server at mcp.churnkey.co.
sentinelx
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist. Remote server at mcp.sentinelx.app.