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/heindewilde/yungle-clientsWrote 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/heindewilde/yungle-clients/mcp-server-yungle)<a href="https://agentmods.dev/mcp/heindewilde/yungle-clients/mcp-server-yungle"><img src="https://agentmods.dev/badge/mcp/heindewilde/yungle-clients/mcp-server-yungle/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/heindewilde/yungle-clients/mcp-server-yungle"><img src="https://agentmods.dev/badge/mcp/heindewilde/yungle-clients/mcp-server-yungle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
Grade A, and why
yungle 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 2d 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
{
"yungle": {
"command": "npx",
"args": [
"-y",
"yungle-mcp"
],
"env": {
"YUNGLE_API_KEY": "",
"YUNGLE_API_URL": ""
}
}
}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.
- 2d ago First seen · 13 lines scan A 73d0c5d7f7fb
yungle is an MCP server published in the GitHub repository heindewilde/yungle-clients (1 stars, last pushed today), 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 2026-09-26.
Other mcp servers, from other repositories
anytype-mcp
Official MCP server for Anytype API - your encrypted, local and collaborative wiki. Runs locally from the @anyproto/anytype-mcp npm package. Needs 1 environment variable to run.
openclaw-mcp
MCP server bridging Claude.ai/Desktop with self-hosted OpenClaw via OAuth 2.1. Runs locally from the openclaw-mcp npm package. Needs 4 environment variables to run.
openclaw
Model Context Protocol (MCP) server for OpenClaw AI assistant integration. Runs locally from the openclaw-mcp npm package.
caldav-mcp
CalDAV calendar operations (list, create, update, delete events) as MCP tools. Runs locally from the caldav-mcp npm package. Needs 3 environment variables to run.
memoire
MCP server "memoire" as configured in memi-design/memi. Launched with memi --profile locked mcp start --no-figma.
memi
Memi is the read-only design engineering audit and skill layer for coding agents. Runs locally from the @memi-design/cli npm package.