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 embeddedlayers/mcp-analyticsnpx agentmods add plugins/embeddedlayers/mcp-analytics/marketplacegit clone --depth 1 https://github.com/embeddedlayers/mcp-analyticsGrade A, and why
mcp-analytics 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 2d 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": "mcp-analytics",
"owner": {
"name": "MCP Analytics",
"email": "[email protected]"
},
"metadata": {
"description": "Data analytics tools for Claude — statistical analysis, machine learning, forecasting, and more. Upload your data, ask a question, get an interactive report.",
"version": "1.0.0"
},
"plugins": [
{
"name": "mcp-analytics",
"description": "Upload a CSV, ask a question, and a team of specialist agents builds a custom analysis you own — regression, clustering, forecasting, A/B tests, churn prediction — delivered as an interactive HTML report with charts and AI insights.",
"version": "1.0.0",
"author": {
"name": "MCP Analytics",
"email": "[email protected]"
},
"homepage": "https://mcpanalytics.ai",
"repository": "https://github.com/embeddedlayers/mcp-analytics",
"license": "MIT",
"keywords": [
"analytics",
"statistics",
"machine-learning",
"forecasting",
"data-analysis",
"csv",
"shopify",
"stripe",
"regression",
"clustering",
"time-series",
"data-science"
],
"source": {
"source": "github",
"repo": "embeddedlayers/mcp-analytics"
}
}
]
}
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.
- 2d ago First seen · 44 lines scan A b7edfbd9b98e
mcp-analytics is a plugin published in the GitHub repository embeddedlayers/mcp-analytics (7 stars, last pushed 8d 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
fast-dash
Fast Dash — turn any Python function into a web app with a single decorator.
scholar-feed
Scholar Feed: research-paper search and literature-review tools for Claude Code.
scholar-feed
Search 600,000+ CS/AI/ML papers with LLM novelty analysis, citation graph, full-text extraction, and BibTeX, without leaving Claude Code. Built for literature reviews.
data-scientist
Cross-platform data science plugin: data readiness, reshaping, statistical and manufacturing analysis, charting, and evidence-backed reporting.
data-scientist
快速数据分析：3 阶段流程（intake → execution → report），单 agent 完成，无多 agent 编排开销。.
My-Jogyo
Scientific research agent extension - turns research goals into reproducible Jupyter notebooks with Python REPL, data analysis, and ML workflows.