# AgentDesk MCP

> Use this tool when you need to ensure the quality and reliability of AI agent outputs, as it provides independent quality gating through adversarial review. The AgentDesk MCP API solves problems of inconsistent or low-quality AI outputs by offering single and dual reviewer modes with structured verdicts and evidence-based checklists. It is ideal for use cases where AI agents require rigorous quality assurance before shipping outputs, accepting inputs from AI models and producing outputs such as PASS/FAIL/CONDITIONAL_PASS scores and categorized issues.

Canonical page: https://skillsregistry.net/skills/ezark-consulting-agentdesk-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ezark-consulting-agentdesk-mcp

## Description

Adversarial AI review API — independent quality gating for AI agent outputs. Provides single and dual reviewer modes with structured verdicts (PASS/FAIL/CONDITIONAL_PASS), scores (0-100), categorized issues, and evidence-based checklists. Built for AI agents that need reliable quality assurance before shipping outputs.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-05-13

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/ezark-consulting/agentdesk-mcp)

## 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": "ezark-consulting-agentdesk-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ezark-consulting-agentdesk-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ezark-consulting-agentdesk-mcp/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