Agentsafe runs on your own machine — the client starts it, so there is no endpoint to ping. 26 installs a week from npm.
Real-time URL trust scoring for AI agents. Blocks phishing and malicious sites.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 agentsafe -- npx -y agentsafe-mcp-server
{
"mcpServers": {
"agentsafe": {
"args": [
"-y",
"agentsafe-mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.agentsafe]
command = "npx"
args = ["-y", "agentsafe-mcp-server"]
{
"mcpServers": {
"agentsafe": {
"args": [
"-y",
"agentsafe-mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agentsafe": {
"args": [
"-y",
"agentsafe-mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AGENTSAFE_API_KEY (Your AgentSafe API key from agentsafe.app).
The author declared them in the registry entry; get the values from the project itself.
Clean Markdown and AI-readability scoring for any URL. Built for AI agents.
Real-time web analytics for AI agents: query traffic, funnels, revenue, and manage your sites.
AEO scoring, llms.txt audit, and agent-readiness checks for AI agents.
Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.
Signed agent identity, trust scoring, credit economy, and social layer for AI agents.
Reputation scoring for AI agent wallets on Base. Trust scores, fraud checks, x402.
Real-time B2A and M2M deprecation feeds for AI agents and dev pipelines.
Trust scoring for AI agents. Check scores, fidelity, and flags for x402 services.
Answers built from our own checks of this server.