Distill Mcp

io.github.hybridforgelabPublished by GitHub account hybridforgelabv0.2.3Updated Nov 6, 2026

Web pages to clean Markdown for AI agents, honouring robots.txt and AI opt-outs.

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Converts web pages or supplied HTML into clean Markdown for AI agents, respecting robots.txt and AI opt-outs, via the paid Distill API.

What you can do
  • Fetch a URL and return its main content as Markdown, with title, author, date and language
  • Convert HTML you already have into Markdown without fetching anything
  • Report a status and note when a site refuses access through robots.txt, an opt-out or bot protection
  • Return the API's JSON response, including remaining monthly quota when the marketplace reports it
When to use it
Useful when an assistant needs readable article text from web pages rather than raw HTML, or when you want page extraction that honours robots.txt and AI opt-outs. It suits light, occasional use on a free or low-cost API plan.
Requirements
Runs locally over stdio with uvx (Python 3.10+, installed by uv). Needs a RapidAPI key in RAPIDAPI_KEY or an api.market key in API_MARKET_KEY; HFL_MARKETPLACE picks the marketplace when both keys are set. Network access to the Distill API is required.
Before you install
The Distill API is paid: each tool call counts as one request on your plan, and the free Basic plan allows 15 requests a month. Page content and any local file paths you pass are sent to the API for processing. The server starts without a key, but tool calls then fail with instructions on getting one.

Installation

In SourceWeft

  1. Open Distill Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Distill MCP server

[M8ven Score] [CI] [PyPI] [Python 3.10+] [License: MIT]

Give your AI agent clean Markdown from any web page: the main content only, without navigation, ads or scripts. Distill honours robots.txt and AI opt-outs.

The server is open source (MIT). It calls the Distill API, which is paid, with a free plan.

  • You use your own key, from RapidAPI or api.market.
  • Every tool call is one request on your plan.
  • The free Basic plan has 15 requests a month, with a hard limit, so it never runs up a bill.

1. Get a key

marketplace
RapidAPIplans
api.marketstore

2. Add the server to your MCP client

The server runs locally over stdio with uv. Put your key in its environment.

JSON configuration (Claude Desktop, Cursor, VS Code and most clients):

json
{  "mcpServers": {    "distill": {      "command": "uvx",      "args": ["--from", "hybridforgelab-distill-mcp", "distill-mcp"],      "env": { "RAPIDAPI_KEY": "your-rapidapi-key" }    }  }}

Claude Code:

bash
claude mcp add distill --env RAPIDAPI_KEY=your-rapidapi-key -- uvx --from hybridforgelab-distill-mcp distill-mcp

Environment

variablemeaning
RAPIDAPI_KEYyour RapidAPI key
API_MARKET_KEYyour api.market key, used when RAPIDAPI_KEY is not set
HFL_MARKETPLACErapidapi or apimarket, when both keys are set

Without a key the server still starts. The first tool call then explains where to get one.

Also listed on Glama:

[distill-mcp on Glama]

3. Tools

toolwhat it does
fetch_markdown(url, max_chars=20000, include_links=True, include_images=False, include_tables=True)fetches the page and returns its main content as Markdown, with the title, author, date and language
html_to_markdown(html, base_url=None, …)the same, for HTML you already have; nothing is fetched

When a site refuses (robots.txt, a noai directive, bot protection), status says so and a note asks the agent to respect it. Don't fetch the page another way: the terms forbid it.

status is ok on success. Other values (robots_txt, opted_out, blocked, not_html, http_error, unreachable) explain why there is no content.

Every tool returns the API's JSON response.

  • When the marketplace reports it, quota_remaining is added: the requests left on your plan this month.
  • Errors are explained in plain words, with what to do next:
    • key refused, with the link to subscribe;
    • quota reached, with the plans;
    • input the API couldn't process, with the API's reason.

Privacy

  • Local files are read only when a tool is given their path. They are sent to the API for that one request.
  • The API processes inputs in memory and doesn't store them. See the privacy policy.
  • Your key is only sent to the marketplace you chose.

Limits

  • html up to 5 MB.
  • Only HTML pages; PDFs and other files are refused (use Unfold for documents).
  • The server needs Python 3.10+ (uv installs it for you).

Development

bash
uv venv && uv pip install -e ".[dev]".venv/bin/pytest            # unit tests, no network; 100% coverage required.venv/bin/ruff check src tests scripts

scripts/e2e_stdio.py distill runs the server over stdio, as a client would, and calls its tools against the real API. It needs RAPIDAPI_KEY or API_MARKET_KEY.

Licence

MIT. Distill itself is a paid API with a free plan, run by Hybrid Forge Lab.

Source: README.md at commit 4f6e466

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the package type cannot run in the sandbox.

Version history

3
  1. v0.2.3LatestNov 6, 2026
  2. v0.2.2Nov 3, 2026
  3. v0.2.0Nov 3, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts