MCP SERVERFetch a URL in the form you actually need it — raw source, fully rendered HTML from a headless browser, structured Markdown, or the article body with the navigation stripped away.
LABSCO SUMMARY
Each tool takes url and nothing else, so discovering that a page renders itself client-side costs one more call to get_rendered_html rather than a configuration change. The vendor's own steer is that get_markdown is the default for readable extraction and get_markdown_summary the choice when only the article body matters, with get_raw_text reserved for content where rendering would be wasted work.
A web-fetching server that returns one URL in a chosen representation, from unrendered source through to a de-chromed Markdown extract.
Nothing — no account, no key.
One command — npx -y mcp-server-fetch-typescript
USE CASES
Pull the main content area as Markdown, and fall back to the full page conversion when the extraction cuts something you needed.
Render the page in a headless browser first so client-side content exists, then convert what came back into readable Markdown.
Take the source as it is served, without a browser between you and the bytes.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
get_markdownConverts web page content to well-formatted Markdown, preserving structural elements like tables and definition lists. Recommended as the default tool for web content extraction when a clean, readable text format is needed while maintaining document structure.
get_markdown_summaryExtracts and converts the main content area of a web page to Markdown format, automatically removing navigation menus, headers, footers, and other peripheral content. Perfect for capturing the core content of articles, blog posts, or documentation pages.
get_raw_textRetrieves raw text content directly from a URL without browser rendering. Ideal for structured data formats like JSON, XML, CSV, TSV, or plain text files. Best used when fast, direct access to the source content is needed without processing dynamic elements.
get_rendered_htmlFetches fully rendered HTML content using a headless browser, including JavaScript-generated content. Essential for modern web applications, single-page applications (SPAs), or any content that requires client-side rendering to be complete.
BEFORE YOU INSTALL
4 tools when we connected.
npx on PATH
CONTEXT COST
Rated by the size of the 4 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Add the block to your client, or run the command directly.
{
"mcpServers": {
"mcp-server-fetch-typescript": {
"command": "npx",
"args": [
"-y",
"mcp-server-fetch-typescript"
]
}
}
}npx -y mcp-server-fetch-typescriptMCP servers
Crawleo
just-every
bhubbb
securecoders