MCPLow riskUnclaimed

MCPSentinel

Precision-first security scanning for Model Context Protocol servers.

gentaArnezzigentaarnezzi/mcpsentinel★ 1Updated Sep 21, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.gentaArnezzi/mcpsentinel",
  "description": "Precision-first security scanning for Model Context Protocol servers.",
  "title": "MCPSentinel",
  "repository": {
    "url": "https://github.com/gentaArnezzi/MCPSentinel",
    "source": "github"
  },
  "version": "0.8.8",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "mcp-guardian-scan",
      "version": "0.8.8",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Comma-separated MCP server hostnames, optionally with an exact port, that the MCP-native scanner may connect to.",
          "isRequired": true,
          "format": "string",
          "name": "MCPSENTINEL_ALLOWED_HOSTS"
        },
        {
          "description": "Set to true only to permit an explicitly allowlisted private or reserved HTTP address in a trusted local network.",
          "format": "string",
          "name": "MCPSENTINEL_ALLOW_PRIVATE_HTTP_TARGETS"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:mcp-guardian-scan@0.8.8
Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.8.8latestOct 7, 2026