Redproof runs on your own machine — the client starts it, so there is no endpoint to ping.
Security checks for apps built with AI tools: scan a GitHub repo and read the fix prompts.
Today is the operative word: we check Redproof 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 redproof -- npx -y redproof-mcp
{
"mcpServers": {
"redproof": {
"command": "npx",
"args": [
"-y",
"redproof-mcp"
]
}
}
}
[mcp_servers.redproof]
command = "npx"
args = ["-y", "redproof-mcp"]
{
"mcpServers": {
"redproof": {
"command": "npx",
"args": [
"-y",
"redproof-mcp"
]
}
}
}
{
"servers": {
"redproof": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"redproof-mcp"
]
}
}
}
Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.
Scan, monitor and fix a live web app from your editor: graded security reports with fix prompts.
Independent security review for AI-built apps. Watch a GitHub repo. Never a patch.
Free read-only check of a public GitHub repo for eight security signals related to the EU CRA.
Scan a website for SEO, accessibility, performance and security issues, and read the report.
Find what a repository's CI is missing, and which security checks cannot fail the build.
Grade a site's security headers with fixes and a badge; read logs or code for the defender.
Audit GitHub repos for malicious and supply-chain code before you depend on them.
Answers built from our own checks of this server.