io.github.vitas/evidra

Official

Evidra

Evidra — Flight recorder for AI infrastructure agents

Flight recorder and monitoring system for AI infrastructure.

Install

Configuration

Environment variables

EVIDRA_ENVIRONMENT

Environment label (production, staging, development)

EVIDRA_EVIDENCE_DIR

Directory for evidence JSONL storage

EVIDRA_SIGNING_MODE

Signing mode: strict (default) or optional (ephemeral local mode)

EVIDRA_SIGNING_KEYsecret

Base64-encoded Ed25519 private key (required for strict mode)

EVIDRA_SIGNING_KEY_PATH

Path to PEM-encoded Ed25519 private key (required for strict mode if key not inline)

claude_desktop_config.json

{
  "mcpServers": {
    "evidra": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/vitas/evidra-mcp:0.4.7"
      ],
      "env": {
        "EVIDRA_ENVIRONMENT": "<YOUR_EVIDRA_ENVIRONMENT>",
        "EVIDRA_EVIDENCE_DIR": "<YOUR_EVIDRA_EVIDENCE_DIR>",
        "EVIDRA_SIGNING_MODE": "<YOUR_EVIDRA_SIGNING_MODE>",
        "EVIDRA_SIGNING_KEY": "<YOUR_EVIDRA_SIGNING_KEY>",
        "EVIDRA_SIGNING_KEY_PATH": "<YOUR_EVIDRA_SIGNING_KEY_PATH>"
      }
    }
  }
}