mdapi — HTML to Markdown for AI agents

Web page or HTML to clean LLM-ready Markdown or JSON. x402 pay-per-call, $0.005, no API key.

Should I use this

Quality & Safety

B
Description quality
90%
Schema completeness
70%
Naming quality
80%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'service_info' description lacks action verbin service_info

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~470Tokens (tool definitions)
~1.1 KBTypical response size
Minimal attention impact (0.37% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "mdapi": {
      "url": "https://md.fastdb.in/mcp"
    }
  }
}

Remote endpoints

https://md.fastdb.in/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟡html_to_markdown(url, html, mode, render)

Convert a web page (by URL) or raw HTML into clean, LLM-ready Markdown. Readability article extraction; nav/scripts/footers stripped; tables preserved. Set render=true to execute the page in a real headless browser first — required for JS-rendered SPAs (React/Next/Vue) that return empty HTML to a plain fetch. Paid tool: $0.005 per call via x402 (USDC on Base).

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Public http(s) URL of the page to fetch and convert"
    },
    "html": {
      "type": "string",
      "description": "Raw HTML to convert instead of fetching a URL"
    },
    "mode": {
      "type": "string",
      "enum": [
        "article",
        "full"
      ],
      "description": "article (default): main content only via Readability. full: whole page."
    },
    "render": {
      "type": "boolean",
      "description": "true: execute the page in a headless browser before converting (JS-rendered SPAs)"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢extract_page(url, html, mode)

Extract structured JSON from a web page (by URL) or raw HTML: title, byline, excerpt, siteName, publishedTime, language, plain text, links, images, and meta tags. Paid tool: $0.005 per call via x402 (USDC on Base).

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Public http(s) URL of the page to fetch and convert"
    },
    "html": {
      "type": "string",
      "description": "Raw HTML to convert instead of fetching a URL"
    },
    "mode": {
      "type": "string",
      "enum": [
        "article",
        "full"
      ],
      "description": "article (default): main content only. full: whole page."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪service_info

Free. Service, pricing, and payment details for the mdapi tools on this server.

Input Schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools
verifiedversion not recorded3 tools