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/yerbymatey/opentrons-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/mcp/yerbymatey/opentrons-mcp/opentrons-mcp)<a href="https://agentmods.dev/mcp/yerbymatey/opentrons-mcp/opentrons-mcp"><img src="https://agentmods.dev/badge/mcp/yerbymatey/opentrons-mcp/opentrons-mcp/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/yerbymatey/opentrons-mcp/opentrons-mcp"><img src="https://agentmods.dev/badge/mcp/yerbymatey/opentrons-mcp/opentrons-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
opentrons-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 12d 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
{ "opentrons-mcp": { "command": "npx", "args": [ "-y", "opentrons-mcp" ] } }
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.
- 12d ago First seen · 9 lines scan A 7c2b8765adb7
opentrons-mcp is an MCP server published in the GitHub repository yerbymatey/opentrons-mcp (7 stars, last pushed 1y 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
thermal-mcp-server
MCP server for datacenter GPU liquid cooling thermal analysis. Runs locally from the thermal-mcp-server Python package.
thermocouple-its90
NIST ITS-90 thermocouple conversion (types B, E, J, K, N, R, S, T): mV to temperature and back, with cold-junction compensation, verified against all 12,026 NIST reference table points. Runs locally from the thermocouple-its90 Python package.
cictikz
AI-driven TikZ circuit schematics: symbol library, renderer, linter, MCP server, xschem bridge. Runs locally from the cictikz Python package.
genicam-mcp
MCP server "genicam-mcp" as configured in finnhyun12/genicam-mcp. Runs locally from the genicam-mcp Python package.
eeg-mcp
A MCP for real-time EEG: BrainFlow streaming with events, wall-clock replay of existing recordings, stateful online DSP, and stimulation event output to software and hardware (TMS/tES) targets. Runs locally from the eeg-mcp Python package.
gnuradio-mcp-server
MCP server for controlling and querying GNU Radio SDR flowgraphs. Runs locally from the gnuradio-mcp-server Python package.