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/mihai-dinculescu/tapoWrote 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/mihai-dinculescu/tapo/tapo-mcp)<a href="https://agentmods.dev/mcp/mihai-dinculescu/tapo/tapo-mcp"><img src="https://agentmods.dev/badge/mcp/mihai-dinculescu/tapo/tapo-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/mihai-dinculescu/tapo/tapo-mcp"><img src="https://agentmods.dev/badge/mcp/mihai-dinculescu/tapo/tapo-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
tapo-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
{
"tapo-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/mihai-dinculescu/tapo-mcp:0.5.0"
],
"env": {
"TAPO_MCP_USERNAME": "",
"TAPO_MCP_PASSWORD": "",
"TAPO_MCP_DISCOVERY_TARGET": "",
"TAPO_MCP_API_KEY": "",
"TAPO_MCP_DISCOVERY_TIMEOUT": "5",
"OTEL_EXPORTER_OTLP_ENDPOINT": ""
}
}
}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 · 19 lines scan A 48c849a48f81
tapo-mcp is an MCP server published in the GitHub repository mihai-dinculescu/tapo (800 stars, last pushed today), 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
rachio-mcp
MCP server for Rachio sprinkler controllers using the reverse-engineered mobile gRPC API. Runs locally from the rachio-mcp Python package. Needs 1 environment variable to run.
rainbird
MCP server "rainbird" as configured in rudy325/rainbird-mcp. Launched with uv --directory ~/rainbird-mcp run server.py. Needs 2 environment variables to run.
rachio-mcp
MCP server for Rachio sprinkler controllers using the reverse-engineered mobile gRPC API. Runs locally from the rachio-mcp Python package.
lg-tv-remote
MCP server "lg-tv-remote" as configured in OmerLapidot/lg-tv-mcp. Runs ./server/index.js with node.
hubitat-mcp-server
MCP server "hubitat-mcp-server" as configured in solaegis/hubitat-mcp. Runs locally from the @solaegis/hubitat-mcp-server npm package.
ha-mcp
A Home Assistant MCP Server. Runs locally from the ha-mcp npm package.