MCP Skill Sec runs on your own machine — the client starts it, so there is no endpoint to ping. 90 installs a week from pypi. Last commit 31 Aug 2026.
Audit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner.
We read the source, 5 h ago · rules ccca72095570
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.
(r"cat\s+.*\.aws/credentials", "high", "aws cred read"),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 mcp-skill-sec -- uvx mcp-skill-sec
{
"mcpServers": {
"mcp-skill-sec": {
"args": [
"mcp-skill-sec"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-skill-sec]
command = "uvx"
args = ["mcp-skill-sec"]
{
"mcpServers": {
"mcp-skill-sec": {
"args": [
"mcp-skill-sec"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-skill-sec": {
"args": [
"mcp-skill-sec"
],
"command": "uvx"
}
}
}
MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.
Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.
Scan skills, MCP configs, and agent content for injection and supply-chain risks. Offline, no LLM.
Deterministic DOM perception for AppSec red teams and AI agents: live Chrome, attack-surface scans.
Prompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.
Deterministic, no-LLM security scanner for MCP servers, plus an inline proxy gate.
Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.
Deterministic tech stack recommendations, audits, and project estimates. No hallucinations.
Answers built from our own checks of this server.