PluginBench
MCP Server

Evidra MCP Server

io.github.vitas/evidra

What is the Evidra MCP server?

Evidra — Flight recorder for AI infrastructure agents

How to install Evidra

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • 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_KEY
    secret

    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)

~/Library/Application Support/Claude/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>"
      }
    }
  }
}

Related MCP servers

Calcula o DAS do Simples Nacional e quantifica a carga que a alíquota não cobre.

0
Python
MIT
View repository →

Build, publish and read scored forms and quizzes where the score picks the next screen.

JAJapan Utils logo

Japan Utils

Maintained

Japan utilities for AI agents: era, romaji, postal codes, holidays, kana, name splitting.

0
Python
MIT
View repository →
VIVivid MCP logo

Vivid MCP

Maintained

Open a Vivid Business account directly from your AI chat without leaving the conversation.

9
MIT
View repository →

Trust infrastructure for AI agents. Directory, jobs, verification, and 360 feedback.

0
TypeScript
View repository →

Search your video library with natural language and retrieve relevant moments through MCP.