Skip to main content
Glama
Sign In
markfetch-mcp

markfetch-mcp

by asdfas988
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

markfetch-mcp

MCP server for Markfetch — let Claude, Cursor, or any MCP client read any web page as clean markdown or screenshot it, with one line of config.

Built for AI agents: turn a URL into LLM-ready context in one tool call.

Install

Add to your MCP client config (Claude Desktop, Cursor, Windsurf, …):

{
  "mcpServers": {
    "markfetch": {
      "command": "npx",
      "args": ["-y", "markfetch-mcp"],
      "env": { "MARKFETCH_API_KEY": "rk_your_key" }
    }
  }
}

No key? It works out of the box on the public rate-limited demo. Get a free key (500 requests/mo, no card) at https://markfetch.com.

Related MCP server: rasterly-mcp

Tools

Tool

What it does

scrape_url(url)

Fetches the page (real Chromium, waits for it to render) and returns the main content as clean, LLM-ready markdown.

screenshot_url(url)

Returns a PNG screenshot of the page.

Env

  • MARKFETCH_API_KEY — your key (optional; falls back to the demo tier).

  • MARKFETCH_API_BASE — override the API base URL.

MIT licensed.

Available Tools

2 tools
scrape_urlA

Fetch a web page and return its main content as clean, LLM-ready markdown. Use this to give the model the content of a URL.

Inputs: url (required).

screenshot_urlB

Capture a screenshot of a web page as a PNG image.

Inputs: url (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.7/5.0

    Scored across 2 tools

    Disambiguation5/5

    Each tool has a distinct output format and purpose: one returns clean markdown content, the other a PNG screenshot. While both accept a URL, there is no ambiguity about which to use based on the desired result.

    Naming Consistency5/5

    Both tools follow the verb_noun pattern (scrape_url, screenshot_url), making the naming scheme predictable and consistent. No mixed conventions or vague verbs.

    Tool Count3/5

    With only two tools, the server feels minimal but not unreasonable for its focused purpose. It is at the lower end of the typical range, so it is borderline but still acceptable.

    Completeness4/5

    The server covers the two primary ways to consume a web page—text content and visual capture. Minor potential additions like raw HTML or metadata extraction are absent, but these are not core to the stated markdown-focused purpose.

    Resources

    Related MCP Connectors

    Related MCP Servers

    • cleanfetch

      belzorash
      A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to read web pages reliably, returning clean markdown content, hyperlinks, and metadata without navigation or ad noise.
      3
      5 npm
      MIT

    • rasterly-mcp

      rasterly-dev
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to read, screenshot, or convert web pages to PDF using a real headless browser, turning any URL into clean Markdown, a visual image, or a print-ready document.
      82 npm
      MIT
    • JsonLink MCP Server

      JsonLink MCP Serverofficial

      mauriblint
      A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to read any web page as clean Markdown, pull title/description/preview metadata, capture desktop, mobile, or full-page screenshots, and list every link or image on a URL. JavaScript-heavy pages are rendered in a real browser and blocked requests retried through a proxy, so agents can reach content they'd otherwise miss.
      5
      61 npm
      MIT