Readdown Mcp

io.github.zcagPublished by GitHub account zcagv1.0.0Updated Oct 27, 2026

Convert web pages to clean, LLM-optimized Markdown. No browser needed.

VerifiedSTDIODesktop onlyWeb Search & ScrapingFiles & Storage

Overview

AI-generated overview

Local MCP server that fetches web pages over HTTP and converts them into clean, token-efficient Markdown for an assistant.

What you can do
  • Fetch a URL and get back clean Markdown with metadata and a token count
  • Convert an HTML string you already have into Markdown
  • Return page metadata such as title, author and date alongside the converted text
When to use it
Useful when an assistant needs readable page content rather than raw HTML, for example summarizing articles or feeding web text into a context window with fewer tokens. It avoids running a full browser, so it suits lightweight, server-side fetching.
Requirements
Runs as a local stdio process, installed via npx from the GitHub package or the published container image. No authentication, environment variables or headers are declared. Network access is needed to fetch pages.
Before you install
Fetched page content is sent to the assistant's model as part of the conversation, so avoid pointing it at private or internal URLs. It only reads pages; no write actions are described.

Installation

In SourceWeft

  1. Open Readdown 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

readdown-mcp

MCP server for converting web pages to clean, LLM-optimized Markdown.

Lightweight — uses HTTP fetch, no browser needed. Powered by readdown.

Tools

fetch_markdown

Fetch a URL and convert it to clean Markdown with metadata and token count.

convert_html

Convert an HTML string to Markdown. Use when you already have the HTML.

Install

Claude Desktop

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "readdown": {      "command": "npx",      "args": ["-y", "github:zcag/readdown-mcp"]    }  }}

Cursor

Add to .cursor/mcp.json:

json
{  "mcpServers": {    "readdown": {      "command": "npx",      "args": ["-y", "github:zcag/readdown-mcp"]    }  }}

Why readdown?

Most web-fetching MCP servers use @mozilla/readability + turndown (two packages, 65KB). readdown replaces both in a single 5KB package with better LLM optimization:

  • Token-efficient output (fewer tokens = cheaper API calls)
  • Built-in token estimation
  • Metadata extraction (title, author, date)
  • Works server-side with linkedom (no browser DOM needed)

License

MIT

Source: README.md at commit c144dbb

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 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