Mcpskills runs on your own machine — the client starts it, so there is no endpoint to ping. 139 installs a week from npm. Last commit 9 Jun 2026.
Trust scoring for MCP servers, AI skills & npm packages — 15 signals + safety scanning.
Today is the operative word: we check Mcpskills 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 server -- npx -y @mcpskillsio/server
{
"mcpServers": {
"server": {
"args": [
"-y",
"@mcpskillsio/server"
],
"command": "npx"
}
}
}
[mcp_servers.server]
command = "npx"
args = ["-y", "@mcpskillsio/server"]
{
"mcpServers": {
"server": {
"args": [
"-y",
"@mcpskillsio/server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"server": {
"args": [
"-y",
"@mcpskillsio/server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
MCPSKILLS_API_KEY (Optional Pro API key for higher rate limits and full reports.).
The author declared them in the registry entry; get the values from the project itself.
Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to
Query trust scores for MCP servers and agent skills. Check if a tool is safe.
Security scanner for AI agent skills and MCP servers
MCP Server for Agent Reputation & Trust Scoring
Entropy0 MCP server — source trust and URL safety tools for AI agents
Security scanner for AI Agent skills, plugins, and MCP servers with A-F grading.
Security scanner for MCP servers and skills: Unicode injection, patterns, secrets.
Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.
Answers built from our own checks of this server.