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/mehmetnadir/cdpilotWrote 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/mehmetnadir/cdpilot/cdpilot-cdpilot)<a href="https://agentmods.dev/mcp/mehmetnadir/cdpilot/cdpilot-cdpilot"><img src="https://agentmods.dev/badge/mcp/mehmetnadir/cdpilot/cdpilot-cdpilot/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/mehmetnadir/cdpilot/cdpilot-cdpilot"><img src="https://agentmods.dev/badge/mcp/mehmetnadir/cdpilot/cdpilot-cdpilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
cdpilot 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 24d 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
{
"cdpilot": {
"command": "npx",
"args": [
"-y",
"cdpilot",
"mcp"
]
}
}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.
- 24d ago First seen · 10 lines scan A 687e193195f5
cdpilot is an MCP server published in the GitHub repository mehmetnadir/cdpilot (32 stars, last pushed 6d 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 2026-09-29.
Other mcp servers, from other repositories
public-browser
Browse your real profile: -30% tokens, -25% cost, -41% tool calls, -34% tool defs, +40% faster. Runs locally from the public-browser npm package.
custom-chrome-dev-mcp
MCP server "custom-chrome-dev-mcp" as configured in HabaAndrei/custom-chrome-dev-mcp. Runs locally from the custom-chrome-dev-mcp npm package.
tbp
MCP server "tbp" as configured in salviz/termux-browser-pilot. Launched with tbp-mcp.
chrome-bridge-mcp
MCP server with 63 tools for browser automation via Chrome extension. Works on ChromeOS/Crostini. Runs locally from the chrome-bridge-mcp npm package.
mcp
Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary. Runs locally from the @kitewright/mcp npm package.
browser-gateway
AI browser tools with Chrome CDP. Navigate, screenshot, interact. Multi-provider failover. Runs locally from the browser-gateway npm package. Needs 1 environment variable to run.