# Deco Site Loaders

> Use this tool when you need to integrate AI capabilities with Deco-powered websites and applications, enabling AI assistants to interact with site loaders through a standardized interface. It solves problems of tool discovery and execution, handling requests and transforming loader results into compatible responses. The Deco Site Loaders tool takes Deco metadata as input and outputs MCP-compatible responses via Server-Sent Events (SSE).

Canonical page: https://skillsregistry.net/skills/deco-site-loaders  
JSON: https://api.skillsregistry.net/v1/skills/deco-site-loaders

## Description

This Deco MCP server implementation enables AI assistants to interact with Deco site loaders through a standardized interface. Built with the Model Context Protocol SDK and Hono, it dynamically registers site loaders as MCP tools by extracting their schemas from the Deco metadata, allowing AI assistants to discover and invoke these tools via Server-Sent Events (SSE). The server handles tool discovery and execution requests, transforming loader results into MCP-compatible responses, making it ideal for integrating AI capabilities with Deco-powered websites and applications.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/deco-site-loaders)
- **Repository:** <https://github.com/deco-sites/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": "deco-site-loaders"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/deco-site-loaders` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/deco-site-loaders/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