Mcp Create Declarative Agent
Official github skill covering MCP tools, creation for orchestrating AI agents and multi-step workflows.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add mcp-create-declarative-agent npx -- -y @trustedskills/mcp-create-declarative-agent
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"mcp-create-declarative-agent": {
"command": "npx",
"args": [
"-y",
"@trustedskills/mcp-create-declarative-agent"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The mcp-create-declarative-agent skill enables users to define and create AI agents using a declarative configuration format. This allows for specifying agent behavior, tools, memory systems, and other properties in a structured way without requiring imperative coding.
When to use it
- When you want to rapidly prototype an AI agent with predefined capabilities.
- To configure an agent's behavior through a YAML or JSON file instead of writing code.
- When working on projects that require multiple agents with consistent configurations.
- For teams looking to standardize agent creation and management across different environments.
Key capabilities
- Declarative configuration using YAML/JSON
- Agent behavior definition
- Tool integration specification
- Memory system configuration
- Scalable agent deployment
Example prompts
- "Create a declarative AI agent that can answer questions about climate change."
- "Define an agent with memory and access to a specific API tool."
- "Generate a YAML file for an agent that performs data analysis tasks."
Tips & gotchas
- Ensure your configuration files are valid YAML or JSON to avoid errors.
- This skill assumes familiarity with the structure of declarative agent definitions, so review documentation if needed.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🏢 Official
Published by the company or team that built the technology.