Loading connector details…
MCP Fetch Server
MCPOpen SourceMIT29.8
by tatn • Frontend & UI
A Model Context Protocol server that fetches web content and converts it into raw text, rendered HTML, or Markdown for use by agents and tools.
Example Use Cases
- 1
Quickly retrieve raw text (JSON, XML, CSV, TSV, or plain text) from a URL without browser rendering for fast parsing.
- 2
Fully rendered HTML from modern SPAs and sites (including JavaScript execution) using a headless browser.
- 3
Clean, structured Markdown or summarized article content suitable for archiving, documentation, or ingestion into LLM pipelines.
Description
This MCP server provides comprehensive web content retrieval and conversion capabilities, including direct raw text fetching, full browser rendering via Playwright, and conversion to rich Markdown (with tables and definition lists). It offers a focused markdown-summary tool that extracts main article content while removing navigation and chrome. The server is useful for archiving, scraping, and feeding cleaned web content to downstream agents or LLMs.
Capabilities(4 total)
Tools (4)
get_raw_text
Retrieves 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.
url:string*
get_rendered_html
Fetches 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.
url:string*
get_markdown
Converts 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.
url:string*
get_markdown_summary
Extracts 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.
url:string*
Quick Actions
Security
Scanned 3 month(s) agoRisk Level
MINIMAL
Read-only data retrieval, no side effects
Trust Score
C59/100
11/17 checks passed
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.
Quick Stats
Service TypeMCP
Pricing ModelFree
Capabilities4 Tools / 0 Prompts / 0 Resources
Ownertatn
CategoryFrontend & UI
DependenciesStandalone
Tags
Raw textHeadless renderingMarkdownSummarization