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/paracetamol951/P-Link-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/mcp/paracetamol951/p-link-mcp/caisse)<a href="https://agentmods.dev/mcp/paracetamol951/p-link-mcp/caisse"><img src="https://agentmods.dev/badge/mcp/paracetamol951/p-link-mcp/caisse/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/paracetamol951/p-link-mcp/caisse"><img src="https://agentmods.dev/badge/mcp/paracetamol951/p-link-mcp/caisse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
caisse 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 9d 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
{
"caisse": {
"command": "node",
"args": [
"D:\\Projets\\Crypto\\P-Link-MCP\\build\\stdio.js"
],
"cwd": "D:\\Projets\\Crypto\\P-Link-MCP",
"env": {
"APIKEY": "7v9HZ3T0Z6Ek9SyqKbyHhN"
}
}
}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.
- 9d ago First seen · 12 lines scan A fd7bed2a9db5
caisse is an MCP server published in the GitHub repository paracetamol951/P-Link-MCP (2 stars, last pushed 5mo ago), licensed Apache-2.0. 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
labelgrid-mcp
Official LabelGrid MCP server — manage your music catalog, releases, analytics and distribution. Runs locally from the @labelgrid/mcp npm package. Needs 7 environment variables to run.
rendex-mcp
Render HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages. Runs locally from the @copperline/rendex-mcp npm package. Needs 1 environment variable to run.
crawlora
MCP server "crawlora", hosted remotely at mcp.crawlora.net, as configured in Crawlora-org/crawlora-mcp.
orizn-visa-mcp
Visa and entry requirements for any passport/destination pair, in 15 languages. Free key. Runs locally from the orizn-visa-mcp npm package. Needs 1 environment variable to run.
crawlora-mcp
Hosted MCP: 795 structured web-data tools for search, maps, commerce, social, gaming & finance. Remote server at mcp.crawlora.net.
newsline
News from 17 outlets with left/center/right bias tags and one-sided blindspot detection. Remote server at news.heyitsmejosh.com.