Html To Markdown Mcp
Convert scraped HTML into Markdown or plain text so web-scraping agents can feed LLMs and docs pipelines without noisy tags.
Overview
html-to-markdown-mcp is a MCP server for the Build phase that converts HTML to Markdown or plain text for web-scraping agents.
What is this MCP server?
- Convert HTML strings to Markdown suitable for LLM context and repos
- Strip HTML to plain text when structure is unnecessary
- Built for web-scraping and research agents consuming page HTML
- stdio MCP (@mukundakatta/html-to-markdown-mcp v0.1.0)
- Lightweight alternative to inline BeautifulSoup-style agent scripts
- @mukundakatta/html-to-markdown-mcp version 0.1.0 on npm
- stdio MCP transport per server schema 2025-09-29
- Repository subfolder: mcp-stack/packages/html-to-markdown-mcp
What problem does it solve?
Scraping agents often choke on tag soup in prompts and storage because inline HTML-to-text conversion is inconsistent across skills and sessions.
Who is it for?
Indie builders running research or scraping agents who need a dedicated HTML cleanup step in Claude Code or Cursor.
Skip if: Workflows that only need rendered screenshots, or teams that already use a managed crawl service with built-in markdown export.
What do I get? / Deliverables
After registration, your agent can normalize page HTML into Markdown or plain text via MCP before summarization, indexing, or publishing.
- Markdown or plain-text versions of HTML suitable for LLM and docs use
- Reusable conversion step in multi-agent scraping workflows
Recommended MCP Servers
Journey fit
HTML cleanup is a build-time bridge between browser or fetch output and agent-readable content you store, summarize, or ship in docs. Integrations covers format conversion MCP tools that sit between scrapers and your agent stack, not the scraper transport itself.
How it compares
MCP HTML conversion layer, not a headless browser or site crawler.
Common Questions / FAQ
Who is html-to-markdown-mcp for?
Solo developers and agent builders who fetch or scrape HTML and want reliable Markdown or plain-text conversion inside MCP workflows.
When should I use html-to-markdown-mcp?
Use it after you have HTML from a scraper or API and before you chunk, summarize, or commit content for docs, RAG, or growth content.
How do I add html-to-markdown-mcp to my agent?
Install @mukundakatta/html-to-markdown-mcp from npm, add the stdio MCP server to your agent config, and call conversion tools on HTML payloads in your pipeline.