WebRead
Fetches any public web page as clean Markdown for agents, free tier then $0.002 per page
- Pricing
- Freemium
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 0.1.0
- Listing updated
- 2 days ago
About WebRead
WebRead is a freemium MCP server for files and documents. It runs as a hosted remote server, so there is nothing to install locally.
One tool, read_url, returns a page's main content without navigation, scripts or ads, keeping absolute links plus title and description metadata. The default is 50,000 characters and maxChars can go up to 200,000.
It behaves as a polite fetcher: robots.txt is honoured under the user-agent token WebReadBot on every redirect hop, private and reserved IPs, internal hostnames, non-default ports and other schemes are refused, and each download is capped at 2 MB and 10 seconds. Bad URLs, robots blocks, unsupported content and upstream failures are never charged.
A free preview endpoint returns the first 2,000 characters at 10 calls a minute per IP. Through the remote MCP server you get 30 full reads a day per IP, then $0.002 per call in USDC over x402 with no account or key. Payments settle through the PayAI facilitator. It is one of nine small x402 tools from the same builder.
Install
Run in a terminal
claude mcp add --transport http x402-url-to-markdown https://webread.agentgate.workers.dev/mcpAdd to Settings → Connectors → Add custom connector
https://webread.agentgate.workers.dev/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"x402-url-to-markdown": {
"url": "https://webread.agentgate.workers.dev/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"x402-url-to-markdown": {
"type": "http",
"url": "https://webread.agentgate.workers.dev/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"x402-url-to-markdown": {
"serverUrl": "https://webread.agentgate.workers.dev/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"x402-url-to-markdown": {
"type": "http",
"url": "https://webread.agentgate.workers.dev/mcp"
}
}
}Tools this server provides (1)
Taken from the project documentation; the running server may differ.
- read_url
- Reads a public web page and returns clean Markdown, with an optional maxChars limit.
What it does
- Clean Markdown
- Main content only, with absolute links and page metadata.
- Large pages
- Default 50,000 characters, configurable up to 200,000.
- robots.txt aware
- Checks robots.txt for WebReadBot on every redirect hop.
- SSRF protection
- Refuses private IPs, internal hostnames and non-default ports.
- Pay per read
- 30 free reads a day per IP, then $0.002 per call over x402.
- Free preview
- First 2,000 characters via a no-wallet preview endpoint.
Good for
- Give an agent a readable copy of a documentation page
- Feed article text to an LLM without page clutter
- Prototype a research agent that pays per page
- Test the preview endpoint from curl before wiring it up
Pricing
Freemium
30 free calls/day per IP, then $0.002 per call in USDC over x402
Prices change. Check webread.agentgate.workers.dev before you buy.
WebRead FAQ
What does it cost?
Free for 30 full reads a day per IP (10 a minute), then $0.002 per call in USDC over x402.
Are failed fetches charged?
No. Bad URLs, robots.txt blocks, unsupported content and upstream failures are not charged.
What are the size limits?
2 MB download and 10 seconds per page; output defaults to 50,000 characters, up to 200,000.
Does it respect robots.txt?
Yes, using the user-agent token WebReadBot.
Is WebRead free?
WebRead has a free plan, with paid plans for more usage or features.
How do I add WebRead to Claude Code?
Run this command in your terminal: claude mcp add --transport http x402-url-to-markdown https://webread.agentgate.workers.dev/mcp
What are the best alternatives to WebRead?
The closest alternatives to WebRead are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and ASTra.
Alternatives to WebRead

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

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

ASTra
MCP serverLet agents read, edit, validate and undo Word .docx files with exact operations
Runs locally- 5 tools
- Freemium
- Files and documents

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