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/eunomia-bpf/schedcpWrote 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/eunomia-bpf/schedcp/schedcp)<a href="https://agentmods.dev/mcp/eunomia-bpf/schedcp/schedcp"><img src="https://agentmods.dev/badge/mcp/eunomia-bpf/schedcp/schedcp/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/eunomia-bpf/schedcp/schedcp"><img src="https://agentmods.dev/badge/mcp/eunomia-bpf/schedcp/schedcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
schedcp 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
{
"schedcp": {
"type": "stdio",
"command": "mcp/target/release/schedcp",
"args": [],
"env": {}
}
}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 · 8 lines scan A 19f4a0837ae4
schedcp is an MCP server published in the GitHub repository eunomia-bpf/schedcp (116 stars, last pushed 6mo 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 2026-08-30.
Other mcp servers, from other repositories
screenshot-server
MCP server for web page and cross-platform system screenshots (macOS, Linux, Windows). Runs locally from the universal-screenshot-mcp npm package.
linux-mcp
MCP server "linux-mcp" as configured in Mohabdo21/linux-mcp. Launched with https://github.com/Mohabdo21/linux-mcp/releases/download/v0.2.9/linux-mcp.
unreal-mcp-additional-tools
MCP server "unreal-mcp-additional-tools" as configured in nodormu/unreal-mcp-additional-tools. Runs locally from the unreal-mcp-additional-tools npm package.
antrieb
Validates AI infra code on real VMs. Self-corrects until it works. No containers, no sandboxes. Remote server at antrieb.sh.
safe-ssh-mcp
A secure and scoped SSH MCP server for executing safe read-only diagnostic commands over SSH. Runs locally from the safe-ssh-mcp Python package.
vr-docs
MCP server "vr-docs" as configured in verticalrectangle/pop-maker-studio. Runs /home/alexis/dev/vertrectdirectory/server.py with /home/alexis/dev/vertrectdirectory/.venv/bin/python3.