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.
npx agentmods add mcp/byteask/byteask-embedded-mcp/byteask-embedded-docsgit clone --depth 1 https://github.com/ByteAsk/ByteAsk-Embedded-MCPGrade A, and why
byteask-embedded-docs 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
{
"byteask-embedded-docs": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"byteask-embedded-mcp"
],
"env": {}
}
}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 · 11 lines scan A 7e259c047293
byteask-embedded-docs is an MCP server published in the GitHub repository ByteAsk/ByteAsk-Embedded-MCP (23 stars, last pushed 2mo 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 2026-08-30.
Other mcp servers, from other repositories
jlink-mcp
Debug embedded firmware on real hardware: J-Link probes, Cortex-M faults, RTT logs, GDB. Runs locally from the jlink-mcp npm package. Needs 4 environment variables to run.
jlink
MCP server "jlink" as configured in Klievan/jlink-mcp. Runs out/mcp/standalone.js with node.
agentic-hil
A green build is not enough: Agentic HIL lets an AI agent probe, flash, reset and exchange UART and CAN traffic with a real STM32 or other embedded target, through policy-gated MCP tools instead of a raw debugger shell, so hardware-in-the-loop tests run unattended in CI. Runs locally from the agentic-hil Python…
hardware-logging
MCP server "hardware-logging" as configured in gurul/hardware-logging. Runs locally from the hardware-logging Python package.
regcite
MCP server "regcite" as configured in combax/regcite. Launched with .venv/Scripts/python.exe -m regcite.server.
hwcontract
Temporal assertions for real hardware traces: judge pulse timing, serial logs and decoded events against YAML contracts (MCP server, pytest plugin, GitHub Action). Runs locally from the hwcontract Python package.