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/OceanAlt666/oceanalt-aml-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/oceanalt666/oceanalt-aml-mcp/gemini-extension)<a href="https://agentmods.dev/plugins/oceanalt666/oceanalt-aml-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/oceanalt666/oceanalt-aml-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/oceanalt666/oceanalt-aml-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/oceanalt666/oceanalt-aml-mcp/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
oceanalt-aml-mcp 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 yesterday.
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": "oceanalt-aml-mcp",
"version": "0.7.7",
"description": "Pre-payment checks for AI agents: allow, review or decline before your agent pays.",
"mcpServers": {
"oceanalt": { "url": "https://oceanalt.com/api/mcp", "type": "http" }
}
}
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.
- yesterday First seen · 9 lines scan A ddf20390a9b8
oceanalt-aml-mcp is a plugin published in the GitHub repository OceanAlt666/oceanalt-aml-mcp (0 stars, last pushed yesterday), 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 2026-11-14.
oceanalt-aml-mcp compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| oceanalt-aml-mcpOceanAlt666/oceanalt-aml-mcp | Plugin | 0 | yesterday | MIT | A | — | Gemini CLI |
| drillrLittle-Grebe-Inc/drillr-mcp-server | Plugin | 10 | 4d ago | MIT | A | — | Claude Code |
| blindpayblindpaylabs/blindpay-mcp | Plugin | 9 | yesterday | MIT | A | — | Claude Code |
| blindpayblindpaylabs/blindpay-mcp | Plugin | 9 | yesterday | MIT | A | — | Claude Code |
| firefly-iii-universal-bridgefabianonetto/mcp-server-firefly-iii | Plugin | 24 | 25d ago | MIT | A | — | Gemini CLI |
| drillrLittle-Grebe-Inc/drillr-mcp-server | Plugin | 10 | 4d ago | MIT | A | — | Gemini CLI |
| blindpayblindpaylabs/blindpay-mcp | Plugin | 9 | yesterday | MIT | A | — | Gemini CLI |