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 2mo 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.
- 2mo 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 3mo 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.
msty-local-ops
MCP server "msty-local-ops" as configured in vega-llc/msty-local-ops. Runs locally from the msty-local-ops Python package.
mcp-macos-toolkit
MCP server "mcp-macos-toolkit" as configured in ContractorKeith/mcp-macos-toolkit. Runs locally from the mcp-macos-toolkit npm package.
thermo-control-mcp
MCP server that lets Claude Code / LLMs monitor Mac thermals and control fan speed safely (Apple Silicon M1-M5). Runs locally from the thermo-control-mcp npm package.
strava-mcp-bridge
Use Strava's official MCP from Codex and other local stdio clients without a developer app. Runs locally from the strava-mcp-bridge npm package.
tidesman
MCP server "tidesman" as configured in JeronimoColon/tidesman-mcp. Launched with https://github.com/JeronimoColon/tidesman-mcp/releases/download/v0.3.0/tidesman-.