Security & Testing
malinois.app
Runs passive outside-in security scans of live web apps and explains findings with plain-language fixes.
ENDPOINT 1
https://malinois.app/mcp
MCP server metadata
- Name
- malinois
- Version
- 1.1.0
Malinois checks a deployed web app from the outside for the leaks AI-built apps most often ship: database tables anyone can read (Supabase RLS off, open Firebase rules), secret keys in the JavaScript bundle, and downloadable .env/.git files. It is passive — only the requests a visitor's browser would make. Only check an app the user owns or is authorized to test: ask the user to confirm before setting i_own_this. After the user fixes something, run scan_app again to confirm.
Known tools 2
scan_appRuns a passive, outside-in security check of a live web app and returns a letter grade (A–F), each issue in plain language with fix steps, and a report link.
Inferred read-onlyexplain_findingReturns the plain-language meaning and step-by-step fix for one Malinois finding.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.malinois]
url = "https://malinois.app/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"malinois": {
"type": "http",
"url": "https://malinois.app/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: malinois
Remote MCP URL: https://malinois.app/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"malinois": {
"url": "https://malinois.app/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"malinois": {
"type": "http",
"url": "https://malinois.app/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "malinois",
"transport": "streamable-http",
"url": "https://malinois.app/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.