Agentscore runs on your own machine — the client starts it, so there is no endpoint to ping. 96 installs a week from npm. Last commit 27 Apr 2026.
MCP security trust layer: scan packages, inspect repos, check exposure, monitor changes.
What the code does
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
пакет @agentscore-xyz/mcp-server ссылается на thezenmonster/agentscores
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
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 agentscore -- npx -y @agentscore-xyz/mcp-server{
"mcpServers": {
"agentscore": {
"command": "npx",
"args": [
"-y",
"@agentscore-xyz/mcp-server"
]
}
}
}[mcp_servers.agentscore]
command = "npx"
args = ["-y", "@agentscore-xyz/mcp-server"]{
"mcpServers": {
"agentscore": {
"command": "npx",
"args": [
"-y",
"@agentscore-xyz/mcp-server"
]
}
}
}{
"servers": {
"agentscore": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@agentscore-xyz/mcp-server"
]
}
}
}Alternatives to Agentscore
same job, measured the same wayConnects MCP servers, packages, security checks, and release gates in one repo.
Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.
16 checks on a system-security-plan JSON, in your editor, before a validator returns the package
Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.
Find the right security-disclosure contact for any internet asset (domain, IP, package, repo, app).
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
AEO scan, 16-engine AI report and one-domain security + AEO report with fixes (x402 USDC).
Scores any MCP server before you trust it: free quick check, full paid report, 2-5 way compare.
Agentscore — questions
Answers built from our own checks of this server.