Scout Security runs on your own machine — the client starts it, so there is no endpoint to ping. 67 installs a week from pypi. Last commit 25 Jul 2026.
Deterministic, zero-token security scanner your AI agent calls to find and re-verify issues.
We read the source, 18 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
"(e.g., `; rm -rf /`).",
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.
execFile(
proc = subprocess.run( # noqa: S603 — fixed argv, absolute exe, no shell
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Scout Security and you get told the day something new turns up.
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 scout -- uvx scout-security
{
"mcpServers": {
"scout": {
"args": [
"scout-security"
],
"command": "uvx"
}
}
}
[mcp_servers.scout]
command = "uvx"
args = ["scout-security"]
{
"mcpServers": {
"scout": {
"args": [
"scout-security"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"scout": {
"args": [
"scout-security"
],
"command": "uvx"
}
}
}
Register/verify your domains, queue security scans, and read findings (CVE, severity).
Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.
Deterministic security layer your AI can't be. 462 rules, 39 tools, CLI + doctor + host audit.
Validates AI-generated Python: syntax, lint, security scan and deterministic repair.
Security scanner for AI agent skills and MCP servers
Deterministic authorization and security guard for AI agent actions with signed receipts.
Security scanning and trust verification for AI agent tools.
Self-hosted MCP server: 26 deterministic dev, security, and EVM tools.
Answers built from our own checks of this server.