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/Seraph310/halo-pixelbar-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/seraph310/halo-pixelbar-mcp/gpt-halo-pixelbar-control)<a href="https://agentmods.dev/mcp/seraph310/halo-pixelbar-mcp/gpt-halo-pixelbar-control"><img src="https://agentmods.dev/badge/mcp/seraph310/halo-pixelbar-mcp/gpt-halo-pixelbar-control/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/seraph310/halo-pixelbar-mcp/gpt-halo-pixelbar-control"><img src="https://agentmods.dev/badge/mcp/seraph310/halo-pixelbar-mcp/gpt-halo-pixelbar-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gpt-halo-pixelbar-control 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 11d 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
{ "gpt-halo-pixelbar-control": { "command": "uvx", "args": [ "gpt-halo-pixelbar-control" ] } }
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.
- 11d ago First seen · 8 lines scan A 839a472750f7
gpt-halo-pixelbar-control is an MCP server published in the GitHub repository Seraph310/halo-pixelbar-mcp (2 stars, last pushed 1mo 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
Windows-MCP
Lightweight MCP Server for interacting with Windows Operating System. Runs locally from the windows-mcp Python package.
desktop-touch-mcp
Computer-use MCP for Windows 10/11: 29 tools — screenshot, UIA, Chrome CDP, type/click/scroll, VBA. Runs locally from the @harusame64/desktop-touch-mcp npm package. Needs 6 environment variables to run.
gpt-web-codex
MCP server "gpt-web-codex" as configured in m4j2rpf766-crypto/gpt-web-codex. Runs locally from the gpt-web-codex npm package.
etw-mcp
MCP server "etw-mcp" as configured in nijosmsft/etw-mcp. Runs locally from the etw-mcp Python package.
clawtouch-mcp
MCP stdio server exposing HID mouse/keyboard tools backed by ClawTouch Pico hardware. Runs locally from the clawtouch-mcp Python package.
windows-operations-mcp
MCP server "windows-operations-mcp" as configured in sandraschi/windows-operations-mcp. Runs locally from the windows-operations-mcp Python package.