# web-perception-mcp

> Use this tool when you need to analyze webpages and understand their structure and content for AI coding assistants. It solves problems of inaccurate page understanding by combining DOM extraction with MiniMax vision, providing context-rich insights. The tool takes webpage URLs as input and outputs detailed structural and visual analysis for informed decision-making.

Canonical page: https://skillsregistry.net/skills/javigala-web-perception-mcp  
JSON: https://api.skillsregistry.net/v1/skills/javigala-web-perception-mcp

## Description

A DOM-first, vision-second MCP server for webpage analysis, combining structural DOM extraction with MiniMax vision to provide accurate, context-rich page understanding for AI coding assistants.

## Trust

- **Trust score (0–1):** 0.79
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/e1o1b85273)
- **Repository:** <https://github.com/JaviGala/web-perception-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": "javigala-web-perception-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/javigala-web-perception-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/javigala-web-perception-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