# pipeworx-io/mcp-htmltext

Source: https://glimind.com/server/glama%2Fpipeworx-io%2Fmcp-htmltext
Registry id: `glama/pipeworx-io/mcp-htmltext`
Status: unknown

## Tools (3)

- `extract_links`: Extract all hyperlinks from HTML as {href, text} pairs.
- `extract_metadata`: Pull page metadata from HTML: title, description, keywords, and Open Graph tags.
- `html_to_text`: Convert HTML to readable plain text, stripping scripts, styles, and comments.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.