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/gondola-ai/gondola-mcpWrote 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/plugins/gondola-ai/gondola-mcp/gemini-extension)<a href="https://agentmods.dev/plugins/gondola-ai/gondola-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/gondola-ai/gondola-mcp/gemini-extension/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/plugins/gondola-ai/gondola-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/gondola-ai/gondola-mcp/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gondola 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 4d 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
{
"name": "gondola",
"version": "0.1.0",
"description": "Cash-vs-award travel search: hotels, flights, and rental cars across every major loyalty program, with cents-per-point valuations, loyalty tracking, rate alerts, and direct booking.",
"mcpServers": {
"gondola": {
"httpUrl": "https://mcp.gondola.ai/mcp/auth"
}
},
"contextFileName": "GEMINI.md"
}
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.
- 4d ago Changed a381f851513a
- 1mo ago First seen · 12 lines scan A df37182b6e45
gondola is a plugin published in the GitHub repository gondola-ai/gondola-mcp (9 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-17.
Other plugins, from other repositories
maqami-travel
Official MCP server for MAQAMI, a hotel and flight booking platform with 3M+ hotels. Search hotels and flights, read hotel details, then send the customer a secure checkout link on book.maqami.co. Remote Streamable HTTP endpoint, no API key required.
maqami-travel
Official MCP server for MAQAMI, a hotel and flight booking platform with 3M+ hotels.
google-flights
Hosted Google Flights MCP for Cursor: live fares with Google's own low/typical/high verdict. Sign in with Google or bring your own RapidAPI key. Ad-free.
google-flights
Hosted Google Flights MCP: live fares with Google's own low/typical/high verdict. BYO RapidAPI key. Ad-free.
flightclaw
Search Google Flights, price-track routes and get alerts when fares drop, then book and pay through Duffel. Remembers travellers, companions, loyalty programmes, cards and cabin preferences so options come back ranked for the person asking.
award-travel-finder
Search award flight availability across 28 airlines, award-chart pricing for 23 loyalty programs, and award nights at Marriott, Hilton, IHG and Hyatt. 127 tools, OAuth sign-in, no API key.