readfetch runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 1 Nov 2026.
Stdio MCP: free probe; paid web reading (text/map/scrape) via x402 on readfetch.com
Today is the operative word: we check readfetch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-x402-proxy -- npx -y @readfetch/mcp-x402-proxy
{
"mcpServers": {
"mcp-x402-proxy": {
"command": "npx",
"args": [
"-y",
"@readfetch/mcp-x402-proxy"
]
}
}
}
[mcp_servers.mcp-x402-proxy]
command = "npx"
args = ["-y", "@readfetch/mcp-x402-proxy"]
{
"mcpServers": {
"mcp-x402-proxy": {
"command": "npx",
"args": [
"-y",
"@readfetch/mcp-x402-proxy"
]
}
}
}
{
"servers": {
"mcp-x402-proxy": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@readfetch/mcp-x402-proxy"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
EVM_PRIVATE_KEY (Base mainnet wallet for paid tools; omit for readfetch_probe and tools/list only), READFETCH_MAX_PAYMENT_USD (Maximum USD per x402 authorization (default 1, max 100)), READFETCH_MCP_URL (Upstream MCP URL for tools/list (default https://readfetch.com/mcp)), READFETCH_DEV (Set to 1 for localhost/Sepolia dev only; never with production READFETCH_MCP_URL).
Post-quantum readiness of any website, PQC adoption figures, the probe map; paid checks via x402.
Markdown scrape, site map, page metadata, screenshots, web search and PDF to text. Pay per call
Read pages & files to text, news, weather, market holidays and timezones via x402.
Firecrawl web data: scrape, map, search, crawl, extract, research, and llms.txt.
Scrape, crawl, and map websites to Markdown or JSON via local CLI.
46 tools free here (rate-limited); 31 REST routes pay-per-call via x402 on Base.
Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools
Web scraping for agents: scrape, crawl, map, search and extract pages as clean markdown or JSON.
Answers built from our own checks of this server.