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/Bennyyy28/claude-gpt-launcherWrote 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/bennyyy28/claude-gpt-launcher/claude-gpt-launcher)<a href="https://agentmods.dev/mcp/bennyyy28/claude-gpt-launcher/claude-gpt-launcher"><img src="https://agentmods.dev/badge/mcp/bennyyy28/claude-gpt-launcher/claude-gpt-launcher/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/bennyyy28/claude-gpt-launcher/claude-gpt-launcher"><img src="https://agentmods.dev/badge/mcp/bennyyy28/claude-gpt-launcher/claude-gpt-launcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
claude-gpt-launcher 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 12d 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
{ "claude-gpt-launcher": { "command": "npx", "args": [ "-y", "claude-gpt-launcher" ] } }
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.
- 12d ago First seen · 9 lines scan A 3dcf9ea6722e
claude-gpt-launcher is an MCP server published in the GitHub repository Bennyyy28/claude-gpt-launcher (0 stars, last pushed 2mo 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
atomlane
MCP server "atomlane" as configured in cloudguo123/atomlane. Runs ./scripts/mcp_server.py with python3.
claudexor
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context. Runs locally from the claudexor npm package.
claudexor
MCP server "claudexor" as configured in razzant/claudexor. Launched with claudexor mcp serve.
chrome-devtools
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.
codebay
MCP server "codebay", hosted remotely, as configured in khromov/codebay.
mochi
MCP server "mochi", hosted remotely at mochi.fast, as configured in khromov/codebay.