Akf runs on your own machine — the client starts it, so there is no endpoint to ping. 242 installs a week from pypi. Last commit 24 Oct 2026.
Trust metadata for AI agents — check files before building on them, stamp verified work.
We read the source, 1 d ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
subprocess.run(["launchctl", "load", str(plist_path)],
__import__(name)
path = os.path.join(cards_dir, f"{card.id}.json")
replay.command, shell=True, cwd=cwd,
document.getElementById('content').innerHTML = html;
<script src="https://appsforoffice.microsoft.com/lib/1/hosted/office.js"></script>
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check Akf every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add akf -- uvx mcp-server-akf
{
"mcpServers": {
"akf": {
"command": "uvx",
"args": [
"mcp-server-akf"
]
}
}
}
[mcp_servers.akf]
command = "uvx"
args = ["mcp-server-akf"]
{
"mcpServers": {
"akf": {
"command": "uvx",
"args": [
"mcp-server-akf"
]
}
}
}
{
"servers": {
"akf": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-server-akf"
]
}
}
}
Human in the loop for AI agents: ask ID verified people to check a decision before acting.
Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.
Memory for coding agents, checked against the filesystem and git before it is believed.
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.
MCP security trust-check for agents before installing MCPs, Skills or tools.
Check the trust/security score of MCP servers, agents, skills & CLIs before you install them.
Evidence-first registry of real-world APIs for AI agents, with verified metadata and comparison.
Answers built from our own checks of this server.