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/Karzone/TestAtlasWrote 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/karzone/testatlas/mcp-testatlas.mcp)<a href="https://agentmods.dev/mcp/karzone/testatlas/mcp-testatlas.mcp"><img src="https://agentmods.dev/badge/mcp/karzone/testatlas/mcp-testatlas.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/karzone/testatlas/mcp-testatlas.mcp"><img src="https://agentmods.dev/badge/mcp/karzone/testatlas/mcp-testatlas.mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
TestAtlas.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 9d 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
{
"TestAtlas.Mcp": {
"command": "TestAtlas.Mcp",
"args": [],
"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.
- 9d ago First seen · 7 lines scan A b230dc3d1d37
TestAtlas.Mcp is an MCP server published in the GitHub repository Karzone/TestAtlas (3 stars, last pushed 3d 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
project-graph-mcp
MCP server for AI agents — project graph, code quality analysis, visual web explorer. JS, TS, Python, Go. Runs locally from the project-graph-mcp npm package.
graftmap
Local-first codebase context engine for AI coding tools. Runs locally from the graftmap npm package.
pare-test
Pare Test ג€” Auto-detects test framework (pytest, jest, vitest, mocha), returns typed JSON. Runs locally from the @paretools/test npm package.
aptu-coder
MCP server "aptu-coder" as configured in clouatre-labs/aptu-coder. Launched with aptu-coder.
test-intel
Coverage analysis, untested function detection and complexity scoring for TS and JS. Runs locally from the @barissozudogru/test-intel-mcp npm package.
waitbus
Workstation-local event bus and blocking wait/emit primitive: let any agent or script wait on or emit CI, pytest, Docker, and filesystem events without polling. GitHub Actions is source #1. Runs locally from the waitbus Python package.