Pageport runs on your own machine — the client starts it, so there is no endpoint to ping. 230 installs a week from npm. Last commit 27 Oct 2026.
Fetch a URL and return its contents as readable markdown text.
Nothing serious here today
Today is the operative word: we check Pageport every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add pageport -- npx -y @reneturcios/pageport{
"mcpServers": {
"pageport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/pageport"
]
}
}
}[mcp_servers.pageport]
command = "npx"
args = ["-y", "@reneturcios/pageport"]{
"mcpServers": {
"pageport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/pageport"
]
}
}
}{
"servers": {
"pageport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/pageport"
]
}
}
}Alternatives to Pageport
same job, measured the same wayAn MCP server that fetches web pages and converts them to clean, readable Markdown.
MCP server fetches URL through a real Chromium browser, returns main content as clean Markdown
Fetch web pages with SSRF protection. Returns clean, readable markdown from any URL.
Search arXiv, fetch paper metadata, and read full-text content.
Download files from URL lists, turn PDFs into Markdown and read text from images. Pay per file.
Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.
Fetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped.
Turn any URL into clean markdown/JSON for AI agents. Self-hostable web content extraction.
Pageport — questions
Answers built from our own checks of this server.