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/glasswarp/mcp-serverWrote 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/glasswarp/mcp-server/glasswarp)<a href="https://agentmods.dev/mcp/glasswarp/mcp-server/glasswarp"><img src="https://agentmods.dev/badge/mcp/glasswarp/mcp-server/glasswarp/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/glasswarp/mcp-server/glasswarp"><img src="https://agentmods.dev/badge/mcp/glasswarp/mcp-server/glasswarp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
glasswarp 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 8d 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
{
"glasswarp": {
"command": "npx",
"args": [
"-y",
"@glasswarp/mcp"
],
"env": {
"GLASSWARP_API_KEY": "${env:GLASSWARP_API_KEY}"
}
}
}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.
- 8d ago First seen · 12 lines scan A 72560e87924a
glasswarp is an MCP server published in the GitHub repository glasswarp/mcp-server (0 stars, last pushed 1mo ago), licensed Apache-2.0. 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
oysterworkflow
MCP server "oysterworkflow" as configured in ShuxinYang111/oysterworkflow. Runs ./mcp/server.mjs with node.
oswright
Playwright-like automation framework for the operating system. Runs locally from the oswright Python package.
kimi-computer-use
MCP bridge for using an existing OpenAI Computer Use installation from Kimi Code CLI on macOS. Runs locally from the kimi-computer-use npm package.
screen-use
MCP server "screen-use" as configured in tongriyaotxt/screen-use. Runs locally from the screen-use Python package.
claude-codex-computer-use
MCP bridge for using an existing OpenAI Computer Use installation from Claude Code on macOS. Runs locally from the claude-codex-computer-use npm package.
agent-computer-use-mcp
A local MCP server for Gateway-managed computer use with cua-driver, OCR, and user-only desktop overlays. Runs locally from the agent-computer-use-mcp npm package.