# evidra

> evidra — vitas-evidra. Use this tool when you need to monitor and track the behavior of AI infrastructure agents, detect patterns, and ensure accountability through a tamper-evident evidence chain. It solves problems related to transparency, reliability, and compliance in AI operations by capturing intent and outcome data. The evidra tool takes in agent activity data and outputs signed evidence chains and reliability scorecards, making it ideal for use cases requiring audit trails and performance monitoring.

Canonical page: https://skillsregistry.net/skills/vitas-evidra  
JSON: https://api.skillsregistry.net/v1/skills/vitas-evidra

## Description

Open-source MCP execution-evidence recorder: wraps one upstream MCP server and records what an agent declared, what the proxy observed, and what it reported — a signed local chain for humans to reconcile.

## Trust

- **Trust score (0–1):** 0.46
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** devops-ci
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/vitas/evidra)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "vitas-evidra"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vitas-evidra` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vitas-evidra/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt