Foundrynet Scrape

io.github.FoundryNetPublished by GitHub account FoundryNetv1.0.1Updated Oct 24, 2026

x402-gated web extraction gateway. Tools: extract, extract_batch.

The publisher's own server: Scrape.ly

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingData & Analytics

Overview

AI-generated overview

Remote MCP gateway that fetches web pages and returns clean text, markdown or JSON, paid per call in USDC via x402 or with a Forge key.

What you can do
  • Extract the main content of a single web page as text, markdown or structured JSON, with scripts, navigation and ads stripped.
  • Extract up to 20 URLs in one batch call at a lower per-URL price.
  • Return an x402 payment_required object when no key is supplied, so the caller can settle payment.
When to use it
Useful for research, content and data agents that need to read arbitrary web pages as clean text or markdown without building their own scraper. Batch extraction suits collecting several pages at once.
Requirements
Remote streamable HTTP endpoint; nothing to install locally. No accounts or API keys are required to list tools. Calls are paid per use in USDC on Solana mainnet via x402, or bypassed with an fnet_ Forge key passed as api_key or an Authorization Bearer header. Network access to the endpoint is needed.
Before you install
Each extraction costs money: $0.01 per single call and $0.008 per URL in batch, settled in USDC on Solana mainnet, so an assistant can spend funds on your behalf. An fnet_ Forge key is a credential and should be kept out of logs and shared transcripts. Requested page URLs are sent to a third-party gateway.

Installation

In SourceWeft

  1. Open Foundrynet Scrape in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.FoundryNet%2Ffoundrynet-scrape/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "foundrynet-scrape": {
      "type": "http",
      "url": "https://foundrynet-scrape-production.up.railway.app/mcp"
    }
  }
}

README

FoundryNet Scrape

x402-gated web extraction gateway for AI agents. Fetch any page and get clean content back — text, markdown, or structured JSON. No API keys, no accounts.

Part of the FoundryNet Data Network. Pay-per-call in USDC (x402) or bypass with an fnet_ Forge key. Also exposed as an MCP server for Smithery/Glama/Claude.

Tools / Endpoints

Tool / RoutePriceDescription
extract — POST /v1/extract$0.01{url, format?: "text"|"markdown"|"json"} → extracted main content
extract_batch — POST /v1/extract/batch$0.008{urls: string[]} (max 20) → array of extracted content (volume discount)

Backends: Mozilla Readability (article extraction) + Turndown (HTML→markdown) + Cheerio (fallback) — all free, no API key. Boilerplate (scripts, nav, ads) is stripped automatically.

MCP

Streamable HTTP endpoint: https://foundrynet-scrape-production.up.railway.app/mcp

claude mcp add --transport http foundrynet-scrape https://foundrynet-scrape-production.up.railway.app/mcp

Tools list without auth (discoverable). Pass an fnet_ key as api_key (or Authorization: Bearer) to bypass payment; otherwise the tool returns an x402 payment_required object.

Payment (x402)

Standard x402 v2 on Solana mainnet USDC. Discovery: GET /x402, GET /.well-known/x402, per-route 402 at GET /x402/{route}. Validated on 402 Index.

The highest-frequency tool category — every research, content, and data agent needs to read the web.

Source: README.md at commit f9dca03

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Scrape integrations

Scrape.ly

ly.scrapeOfficial publisher

Scrape.ly MCP server that lets an assistant search the Scrape.ly Store for Actors, run them, and read their datasets, key-value stores and logs.

Streamable HTTPWeb executableAuth
Web Search & ScrapingCredential requiredNov 7, 2026

SEO Data MCP (SteadyScrape)

Published by GitHub account steadyscrape

Keyword volume, live SERP ranks, domain traffic, ranked keywords, backlinks, Google Trends, YouTube.

Streamable HTTPWeb executableAuth
Web Search & ScrapingCredential requiredNov 3, 2026

x402-scrape-mcp

Published by GitHub account 6mickswagger9

Local MCP server exposing an x402 paid API for AI agents, with payments in USDC on Base via a CDP facilitator.

STDIODesktop only
Web Search & ScrapingNot validated · the server did not startOct 31, 2026

TrueScrape

Published by GitHub account TrueScrape

Paid API that gives an assistant live public data from 52 platforms — social profiles, posts, product listings, property and ad data — plus mention monitoring.

Streamable HTTPWeb executableAuth
Web Search & Scraping200+ toolsNov 4, 2026

Jobs Data MCP (SteadyScrape)

Published by GitHub account steadyscrape

Remote Apify-hosted MCP server that gives an assistant live job postings from 14+ ATS career sites and remote job listings.

Streamable HTTPWeb executableAuth
Web Search & ScrapingCredential requiredNov 6, 2026