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.
/plugin marketplace add shigechika/zapi-mcpnpx agentmods add plugins/shigechika/zapi-mcp/plugingit clone --depth 1 https://github.com/shigechika/zapi-mcpGrade A, and why
zapi-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 yesterday.
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": "zapi-mcp",
"displayName": "Zabbix MCP",
"description": "Zabbix API for Claude Code, via an API user. Investigate active problems, hosts, and item values, get a one-shot daily_brief health check, acknowledge problems, and open maintenance windows. Site-specific daily_brief categories (DHCP pool usage, SNAT usage, core-network, …) need a local ZABBIX_CATEGORIES_INI file that this plugin's own settings cannot supply on someone else's machine; without it daily_brief still works with just the built-in Active Problems / In Maintenance sections. Requires ZABBIX_URL, ZABBIX_USER, and ZABBIX_PASSWORD.",
"author": {
"name": "AIKAWA Shigechika",
"url": "https://github.com/shigechika"
},
"homepage": "https://shigechika.github.io/zapi-mcp/",
"repository": "https://github.com/shigechika/zapi-mcp",
"license": "MIT",
"keywords": [
"zabbix",
"monitoring",
"observability",
"network",
"incident-response",
"maintenance",
"sre"
]
}
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.
- yesterday First seen · 23 lines scan A 4415e87c649a
zapi-mcp is a plugin published in the GitHub repository shigechika/zapi-mcp (0 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 2026-08-31.
Other plugins, from other repositories
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.
cdc-health-mcp-server
Search and query CDC public health data — mortality, vaccinations, surveillance, behavioral risk (Socrata SODA API) via MCP. STDIO or Streamable HTTP.
shotcut-mcp
Full transactional editor for Shotcut projects through a local MCP server.
pmtechdev
Local-first MCP plugins maintained by PMTechDev.
axcient
Every x360Recover endpoint, plus the fleet-wide backup-health answers the API alone can't give — offline, joined, and agent-ready.
identity-forge
Identity Forge tools and agent guidance for design systems and brand work.