Web2MD
Turn web pages into clean Markdown or token-sized RAG chunks via the Web2MD API
- Pricing
- Freemium
- Platforms
- CLI, API
- Runs
- Locally
- Version
- 0.1.0
- Listing updated
- 2 days ago
About Web2MD
Web2MD is a freemium MCP server for web search and scraping. It runs locally on your machine and is started by your AI client.
Web2MD's server wraps a RapidAPI service, so you need a RapidAPI key before it works. It runs locally over stdio from the npm package web2md-rag-mcp and requires Node.js 22 or newer.
The main difference from a plain fetcher is the chunk tool, which splits a page at headings, records each chunk's heading path and keeps it within a token budget you set (64 to 8192, default 512) with optional overlap. Other tools return a page as Markdown, plain text or JSON, convert HTML you already hold, and fetch only metadata.
The backing API respects robots.txt and per-site limits and refuses private network addresses. It handles HTML up to 5 MB and cannot render JavaScript-only pages, which return a no_content error.
Install
Run in a terminal
claude mcp add web2md-mcp --env RAPIDAPI_KEY='<RAPIDAPI_KEY>' -- npx -y web2md-rag-mcpAdd to claude_desktop_config.json
{
"mcpServers": {
"web2md-mcp": {
"command": "npx",
"args": [
"-y",
"web2md-rag-mcp"
],
"env": {
"RAPIDAPI_KEY": "<RAPIDAPI_KEY>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"web2md-mcp": {
"command": "npx",
"args": [
"-y",
"web2md-rag-mcp"
],
"env": {
"RAPIDAPI_KEY": "<RAPIDAPI_KEY>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"web2md-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"web2md-rag-mcp"
],
"env": {
"RAPIDAPI_KEY": "<RAPIDAPI_KEY>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"web2md-mcp": {
"command": "npx",
"args": [
"-y",
"web2md-rag-mcp"
],
"env": {
"RAPIDAPI_KEY": "<RAPIDAPI_KEY>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"web2md-mcp": {
"command": "npx",
"args": [
"-y",
"web2md-rag-mcp"
],
"env": {
"RAPIDAPI_KEY": "<RAPIDAPI_KEY>"
}
}
}
}Configuration
RAPIDAPI_KEYYour RapidAPI key, subscribed to Web2MD (free BASIC plan available).Required
Tools this server provides (4)
Taken from the project documentation; the running server may differ.
- read_url
- Fetch a page as clean Markdown or text.
- chunk_url
- Split a page into heading-aware RAG chunks.
- convert_html
- Convert raw HTML to Markdown or text.
- page_metadata
- Get a page's metadata.
What it does
- Clean page reading
- Main content as Markdown or text without menus and ads.
- Heading-aware chunks
- RAG chunks with heading path and token count.
- HTML conversion
- Convert HTML you supply without fetching.
- Metadata lookup
- Title, author, date, language and reading time.
- Safe fetching
- Respects robots.txt and blocks private network targets.
- Typed errors
- Codes such as robots_disallowed and no_content explain failures.
Good for
- Prepare web pages for embedding in a RAG index
- Give an assistant a clean copy of an article
- Extract metadata for many URLs
- Convert saved HTML to Markdown
Pricing
Freemium, from $9 a month
BASIC free (500 req/mo); PRO $9, ULTRA $29, MEGA $79
Prices change. Check rapidapi.com before you buy.
Web2MD FAQ
What do I need to run it?
Node.js 22 or newer and a RapidAPI key subscribed to Web2MD.
Is there a free plan?
Yes. BASIC is $0 for 500 requests a month; PRO is $9, ULTRA $29 and MEGA $79.
Does it work on JavaScript-only pages?
Not yet. Those return no_content; rendering support is planned.
What is the size limit?
Pages up to 5 MB.
Is Web2MD free?
Web2MD has a free plan, with paid plans for more usage or features. Paid plans start at $9 a month.
How do I add Web2MD to Claude Code?
Run this command in your terminal: claude mcp add web2md-mcp --env RAPIDAPI_KEY='<RAPIDAPI_KEY>' -- npx -y web2md-rag-mcp
What are the best alternatives to Web2MD?
The closest alternatives to Web2MD are Scrapling MCP Server, Firecrawl MCP Server, Claude Code Ultimate Guide, SearXNG Search and NeuralVerge.
Alternatives to Web2MD

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping

NeuralVerge
MCP serverStructured, source-tagged business and people data from 300+ sources for agents
- 200 tools
- Remote
- Free trial
- 1 GitHub star
- Web search and scraping

AI-Powered directory
MCP serverSearch AI tools, agents and MCP servers and get install configs from inside your AI assistant.
- 4 tools
- Remote
- Free
- Developer tools