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/Leonezz/openbaudInstalling this writes the configuration, not the program: `node` runs a file from the repository, so clone it first and make the path in the command match where you put it.
Wrote 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/leonezz/openbaud/openbaud-openbaud)<a href="https://agentmods.dev/mcp/leonezz/openbaud/openbaud-openbaud"><img src="https://agentmods.dev/badge/mcp/leonezz/openbaud/openbaud-openbaud/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/leonezz/openbaud/openbaud-openbaud"><img src="https://agentmods.dev/badge/mcp/leonezz/openbaud/openbaud-openbaud.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
openbaud 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 2mo 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
{
"openbaud": {
"command": "node",
"args": [
"./launcher.mjs",
"mcp"
],
"cwd": ".",
"startup_timeout_sec": 10,
"tool_timeout_sec": 3600
}
}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.
- 2mo ago Changed · +1 lines b850cae2fb1e
- 2mo ago First seen · 11 lines scan A 7693c445f280
openbaud is an MCP server published in the GitHub repository Leonezz/openbaud (7 stars, last pushed 26d 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
serial-mcp
MCP server "serial-mcp" as configured in qarnet/serial-mcp. Launched with https://github.com/qarnet/serial-mcp/releases/download/v0.9.3/serial-mcp-x86_64-.
victron-tcp
MCP server for Victron Energy GX devices via Modbus TCP or MQTT. Runs locally from the victron-tcp npm package. Needs 6 environment variables to run.
arduino-mcp-server
Arduino MCP server for CLI setup, board detection, compile/upload, serial monitoring, and pin refs. Runs locally from the arduino-mcp-server npm package. Needs 2 environment variables to run.
bench
MCP server "bench" as configured in seayniclabs/bench. Launched with bench.
open-dart
OpenDART MCP server with 85 disclosure APIs and verified financial statement Excel workbooks. Runs locally from the opendart-mcp-server Python package. Needs 1 environment variable to run.
servomotor-mcp
MCP server to drive Gearotons M17 open-source servomotors from natural language (Claude / any MCP client) over RS-485. Auto-discovers serial ports and motors; exposes the full firmware command set. Runs locally from the servomotor-mcp Python package. Needs 3 environment variables to run.