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/littleblakew/msds-chain-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/littleblakew/msds-chain-mcp/gemini-extension)<a href="https://agentmods.dev/plugins/littleblakew/msds-chain-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/littleblakew/msds-chain-mcp/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/littleblakew/msds-chain-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/littleblakew/msds-chain-mcp/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
msds-chain 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 9d 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": "msds-chain",
"version": "1.5.11",
"description": "Chemical safety intelligence for AI-assisted lab work — 24 tools for compatibility, hazards, PPE, storage, waste disposal, mixing order, exposure limits, transport classification, regulatory compliance, and signed audit reports, every answer traceable to a specific supplier SDS.",
"mcpServers": {
"msds-chain": {
"httpUrl": "https://mcp.lagentbot.com/mcp",
"oauth": {
"enabled": true
}
}
}
}
What ships with it
17 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.
- scripts/ci/send_alert_email.py 6.7 KB runs code
- scripts/create-container-app.sh 2.8 KB runs code
- scripts/export_cowork_tools.py 1.8 KB runs code
- scripts/export_tool_surface.py 2.9 KB runs code
- scripts/hooks/commit-msg 10 KB
- scripts/hooks/install.sh 10 KB runs code
- scripts/hooks/README.md 6.0 KB
- scripts/lib/ci-skip-token.sh 3.1 KB runs code
- scripts/live_tool_coverage.py 10 KB runs code
- scripts/mcp_surface_adapter.py 3.2 KB runs code
- scripts/mcp_surface_replay.py 7.9 KB runs code
- scripts/refresh_backend_surface.py 10 KB runs code
- scripts/release.sh 5.8 KB runs code
- scripts/setup-oidc.sh 2.4 KB runs code
- scripts/smoke_mcp.py 5.9 KB runs code
- scripts/stamp_derived.py 2.8 KB runs code
- scripts/structured_content_drift.py 6.6 KB runs code
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.
- 9d ago Changed f488086cfbd4
- 15d ago Changed 69cc1c3b6a82
- 20d ago First seen · 14 lines scan A fb58c733fcf9
msds-chain is a plugin published in the GitHub repository littleblakew/msds-chain-mcp (0 stars, last pushed 9d 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 2026-09-26.
Other plugins, from other repositories
horizon-shield
Audit Japanese construction and renovation estimates against the open JCCDB dataset and return Bitcoin-anchored, independently recomputable fair-price receipts. Remote MCP server, read-only, no API key.
alexandria
Query, read, and ingest texts from 152 public digital libraries: academic papers, public domain books, legal records, government archives, security advisories, news, and developer documentation.
agentkey
AgentKey — one-stop live data marketplace for your agent: web search, web scraping, social media, finance, crypto, e-commerce, business data, weather/maps, and travel through a single MCP server. No API keys to manage, auto failover across providers, free to start.
upstash
The Upstash MCP server plus agent skills for every Upstash SDK and CLI — Redis, QStash, Workflow, Box, Blob, Ratelimit, Vector, and Search.
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.
arxiv-mcp-server
Search arXiv, fetch paper metadata, and read full-text content via MCP. STDIO or Streamable HTTP.