Distill MCP server
This server converts web pages or supplied HTML into clean Markdown main content for AI agents.
Fetch a page by URL and return its main content as Markdown with title, author, date, and language.
Convert HTML you already have into Markdown, optionally using a base URL to resolve relative links/images.
Control output with
max_chars,include_links,include_images, andinclude_tables.Respect robots.txt and
noaiopt-outs, reporting statuses such asrobots_txt,opted_out,blocked,not_html,http_error, orunreachablewhen content is unavailable.Return the API JSON response, including
quota_remainingwhen the marketplace reports it.Handle only HTML up to 5 MB; PDFs and other file types are refused.
Integrates with RapidAPI as a marketplace/key provider for the Distill API, allowing the server to use a RapidAPI subscription key to fetch web pages and convert their main content to clean Markdown.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Distill MCP server turn https://example.com/blog/post into clean markdown with title and author"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
hybridforgelab-distill-mcp: moved to bytestay-distill-mcp
This package has moved to bytestay-distill-mcp. Hybrid Forge Lab is now ByteStay.
This last version only installs bytestay-distill-mcp and forwards to it. It prints a one-line notice on stderr and gets no more updates.
Switch
Replace hybridforgelab-distill-mcp with bytestay-distill-mcp in your MCP client config:
"command": "uvx",
"args": ["--from", "bytestay-distill-mcp", "distill-mcp"]Or with Claude Code:
claude mcp add distill --env RAPIDAPI_KEY=your-rapidapi-key -- uvx --from bytestay-distill-mcp distill-mcpThe environment variables are the same, so your keys keep working.
Related MCP server: cleanfetch
Links
Package: bytestay-distill-mcp
Source: Bytestay/distill-mcp
Distill API: distill.bytestay.pt
Available Tools
2 toolsfetch_markdownARead-onlyIdempotent
Fetch a web page and return its main content as Markdown, with title, author, date and language.
status is "ok" on success. Other values (robots_txt, opted_out, blocked, not_html, http_error,
unreachable) explain why there is no content.
Inputs: url (required), max_chars, include_links, include_images, +1 more.
html_to_markdownARead-onlyIdempotent
Turn HTML you already have into clean Markdown (main content only). A noai directive in the HTML is
honoured: the result then has no content.
Inputs: html (required), base_url, max_chars, include_links, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct inputs and purposes: fetch_markdown starts from a URL, while html_to_markdown converts HTML the caller already has. The descriptions make the boundary explicit, so an agent should not confuse them.
Both names use snake_case and are readable, but they follow slightly different construction patterns: fetch_markdown is verb_object, while html_to_markdown is source_to_target. The deviation is minor and does not impede understanding.
Two tools is on the low side generally, but for this narrowly focused markdown-extraction server each tool covers a necessary part of the workflow: fetching a URL and converting existing HTML. The set is well scoped without obvious filler.
The core operations for turning web content into Markdown are covered: URL fetching and HTML conversion. Minor possible gaps, such as batch fetching or raw HTML retrieval, are not essential for the apparent purpose and can be worked around.
Maintenance
Related MCP Connectors
Clean Markdown and AI-readability scoring for any URL. Built for AI agents.
Read any public web page as clean Markdown for LLMs. Respects robots.txt. Free tier; x402 paid API.
Turn public web pages into clean Markdown for LLMs, RAG and AI agents
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Related MCP Servers
- AlicenseAqualityDmaintenanceConverts URLs and raw HTML to clean Markdown, enabling AI assistants to read web pages for summarization, analysis, or ingestion.28 npm1MIT
- AlicenseAqualityCmaintenanceEnables AI agents to read web pages reliably, returning clean markdown content, hyperlinks, and metadata without navigation or ad noise.34 npmMIT
- AlicenseAqualityCmaintenanceEnables AI agents to read clean Markdown from any URL and assess source quality with AI-readability scores.687 npm1MIT
- AlicenseAqualityBmaintenanceFetch any web page as clean Markdown or plain text, split it into heading-aware, token-bounded RAG chunks, convert raw HTML, and read page metadata. Uses the Web2MD API on RapidAPI with your own key (free BASIC plan).442 npmMIT