MicroScrape is an MCP server with 4 tools an agent can call, among them extract_fields, links_url, metadata_url. It answers at https://microscrape-production.up.railway.app/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 20 October 2026, succeeded.
Pay-per-request webpage-to-Markdown extraction for AI agents. $0.005 USDC via x402 on Solana.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
extract_fields | For each entry in fields, returns the trimmed text content of the first element matching that CSS selector. Costs $0.010 USDC on Solana via x402, per call — same price as GET /api/v1/extract. Inputs: url, fields |
links_url | Returns every internal and external link with its anchor text. Costs $0.002 USDC on Solana via x402, per call — same price as GET /api/v1/links. Inputs: url |
metadata_url | Cheap metadata-only extraction, no full-page content. Costs $0.002 USDC on Solana via x402, per call — same price as GET /api/v1/metadata. Inputs: url |
scrape_url | Fetches a public HTTP/HTTPS URL, strips boilerplate, and returns the primary content as clean Markdown. Costs $0.005 USDC on Solana via x402, per call — same price as GET /api/v1/scrape. Inputs: url |
Every block below points at https://microscrape-production.up.railway.app/mcp. Pick your client and copy.
claude mcp add --transport http microscrape https://microscrape-production.up.railway.app/mcp
{
"mcpServers": {
"microscrape": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://microscrape-production.up.railway.app/mcp"]
}
}
}{
"mcpServers": {
"microscrape": {
"url": "https://microscrape-production.up.railway.app/mcp"
}
}
}{
"servers": {
"microscrape": {
"type": "http",
"url": "https://microscrape-production.up.railway.app/mcp"
}
}
}{
"context_servers": {
"microscrape": {
"url": "https://microscrape-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"microscrape": {
"serverUrl": "https://microscrape-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"microscrape": {
"url": "https://microscrape-production.up.railway.app/mcp"
}
}
}name: MicroScrape
version: 0.0.1
schema: v1
mcpServers:
- name: MicroScrape
type: streamable-http
url: https://microscrape-production.up.railway.app/mcp{
"mcpServers": {
"microscrape": {
"httpUrl": "https://microscrape-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"microscrape": {
"type": "http",
"url": "https://microscrape-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"microscrape": {
"url": "https://microscrape-production.up.railway.app/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmicroscrape-production.up.railway.app%2Fmcp&type=streamable_http&id=microscrape&name=MicroScrape
It answered our last check on 20 October 2026 in 360 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
4, as returned by the server's own tools/list on 12 September 2026: extract_fields, links_url, metadata_url, scrape_url.
It answered our last check on 20 October 2026 in 360 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://microscrape-production.up.railway.app/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.luci-hue. Endpoint host: microscrape-production.up.railway.app. ARD identifier: urn:air:io.github.luci-hue:mcp:microscrape.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.