# WebforAI Text Extractor

> Use this tool when you need to extract text content from web pages for AI processing, such as research, content analysis, or information gathering. It takes a URL as input, validates the HTML content, and outputs clean, readable markdown text with configurable options for links, tables, and images. Ideal for use cases requiring efficient and reliable web content extraction, this tool provides a structured format suitable for AI assistants to analyze and process online information.

Canonical page: https://skillsregistry.net/skills/yutakobayashi-webforai-text-extractor  
JSON: https://api.skillsregistry.net/v1/skills/yutakobayashi-webforai-text-extractor

## Description

The WebforAI Text Extractor is a Cloudflare Workers-based MCP server that enables AI assistants to extract and process text content from web pages. Built by Yuta Kobayashi, this implementation uses the webforai library to convert HTML content into clean, readable markdown format with configurable options for handling links, tables, and images. The server exposes a single tool, 'extractWebPageText', which fetches a specified URL, validates that it returns HTML content, and transforms it into a structured format suitable for AI processing. Running on Cloudflare's edge network as a Durable Object, it provides efficient and reliable web content extraction for use cases like research, content analysis, and information gathering from online sources.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/yutakobayashi-webforai-text-extractor)
- **Repository:** <https://github.com/yutakobayashidev/webforai-mcp-server>

## 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": "yutakobayashi-webforai-text-extractor"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yutakobayashi-webforai-text-extractor` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yutakobayashi-webforai-text-extractor/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