web-to-markdown-mcp
This MCP server fetches URLs and returns the main content as clean Markdown. It employs a three-tier strategy: first attempting plain HTTP with content negotiation, then using trafilatura for static HTML extraction, and finally falling back to a headless Chromium browser via patchright for JavaScript-heavy pages. This approach minimizes token usage and handles bot detection.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Fetch article content from JS-rendered pages
- Convert web pages to clean Markdown
- Extract main content while ignoring ads and navigation
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
web-to-markdown-mcp 0.6.0
{
"version": "0.6.0",
"transport": "stdio",
"identifier": "web-to-markdown-mcp",
"registryType": "pypi"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"web-to-markdown-mcp": {
"command": "uvx",
"args": [
"web-to-markdown-mcp==0.6.0"
]
}
}
}Cline
{
"mcpServers": {
"web-to-markdown-mcp": {
"command": "uvx",
"args": [
"web-to-markdown-mcp==0.6.0"
]
}
}
}VS Code
{
"servers": {
"web-to-markdown-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"web-to-markdown-mcp==0.6.0"
]
}
}
}Claude Desktop
{
"mcpServers": {
"web-to-markdown-mcp": {
"command": "uvx",
"args": [
"web-to-markdown-mcp==0.6.0"
]
}
}
}Let your agent find its tools
Find servers like web-to-markdown-mcp from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.