MCPLow riskUnclaimed

Klarion

Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real.

0x1Adi0x1adi/klarion★ 10Updated Sep 20, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.0x1Adi/klarion",
  "description": "Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real.",
  "title": "Klarion",
  "repository": {
    "url": "https://github.com/0x1Adi/Klarion",
    "source": "github"
  },
  "version": "0.4.3",
  "packages": [
    {
      "registryType": "mcpb",
      "identifier": "https://github.com/0x1Adi/Klarion/releases/download/v0.4.3/klarion-mcp-v0.4.3.mcpb",
      "version": "0.4.3",
      "fileSha256": "e467824ca3450f49d53b0a4794006b62a2cabc787a9a62c100497b902b77f92d",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Optional. With a key Klarion adjudicates candidates itself; without one it hands them to the calling agent to judge.",
          "format": "string",
          "isSecret": true,
          "name": "ANTHROPIC_API_KEY"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—bundle
Installs—mcpb:https://github.com/0x1Adi/Klarion/releases/download/v0.4.3/klarion-mcp-v0.4.3.mcpb@0.4.3
Runs install scripts—None
NetworkNoneNone
Needs credentialsANTHROPIC_API_KEYANTHROPIC_API_KEY
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. #10.4.3latestOct 7, 2026