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/vibestackdev/vibe-stackWrote 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/vibestackdev/vibe-stack/browser)<a href="https://agentmods.dev/mcp/vibestackdev/vibe-stack/browser"><img src="https://agentmods.dev/badge/mcp/vibestackdev/vibe-stack/browser/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/vibestackdev/vibe-stack/browser"><img src="https://agentmods.dev/badge/mcp/vibestackdev/vibe-stack/browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
browser 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 2d 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
{
"browser": {
"command": "npx",
"args": [
"-y",
"@anthropic-ai/mcp-server-puppeteer"
]
}
}What else mcp.json configures
This page is one entry in a file that holds 4. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 2d ago First seen · 9 lines scan A b5574687b53f
browser is an MCP server published in the GitHub repository vibestackdev/vibe-stack (8 stars, last pushed yesterday), 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 2026-09-06.
Other mcp servers, from other repositories
nx-mcp
Nx's MCP server: lets the agent read the Nx project graph, look up generators and run tasks in an Nx monorepo. Runs locally from the nx npm package.
copilotkit-docs
CopilotKit's hosted docs server: lets the agent search CopilotKit documentation and examples. Remote server at mcp.copilotkit.ai.
data-table-drizzle
MCP server "data-table-drizzle", hosted remotely at localhost, as configured in openstatusHQ/data-table-filters.
mcp
MCP server for UI Beats. Let your coding agent search, read and install animated React components. Runs locally from the @uibeats/mcp npm package.
aginxbrowser
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions. Remote server at browser.aginx.net.
peek-dev
MCP server "peek-dev" as configured in Cubenest/rrweb-stack. Runs ${CLAUDE_PROJECT_DIR:-.}/packages/peek-mcp/dist/index.js with node.