# Validate, dry-run, and expose YAML agent runbooks as MCP tools with DeclarAgent

> Turn YAML runbooks into auditable agent actions with validation, dry-runs, destructive-step approval, and optional MCP exposure.

- Skill: `agentskillexchange/validate-dry-run-and-expose-yaml-agent-runbooks-as-mcp-tools` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/validate-dry-run-and-expose-yaml-agent-runbooks-as-mcp-tools`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/validate-dry-run-and-expose-yaml-agent-runbooks-as-mcp-tools/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/validate-dry-run-and-expose-yaml-agent-runbooks-as-mcp-tools

---


# Validate, dry-run, and expose YAML agent runbooks as MCP tools with DeclarAgent

Turn YAML runbooks into auditable agent actions with validation, dry-runs, destructive-step approval, and optional MCP exposure.

## Prerequisites

Go, YAML runbooks, MCP-compatible client for MCP mode

## Installation

Basic usage or getting-started notes:
- Validate, dry-run, and safely execute multi-step YAML workflows from any LLM tool-use loop.
- ## Docs: 3 Example Plans You Can Copy and Run
- Or run any plan directly:

- Source: https://github.com/shiehn/DeclarAgent
- Extracted from upstream docs: https://raw.githubusercontent.com/shiehn/DeclarAgent/HEAD/README.md

## Documentation

- https://github.com/shiehn/DeclarAgent

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/validate-dry-run-and-expose-yaml-agent-runbooks-as-mcp-tools-with-declaragent/)