io.github.NyTerryPublished by GitHub account NyTerryv0.1.1Updated Nov 4, 2026
x402-powered AI agent services — URL extraction, PDF processing, code scanning, and more.
The publisher's own server: Machina World Cup Intelligence
Machina's local MCP server; no sign-in required; STDIO; 8 tools.
No AI overview yet: these facts come from the registry entry and the server itself.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
Machina as an MCP server. Use Machina's x402-powered agent services directly from Claude Desktop, Cursor, or any MCP-compatible AI host — no x402 integration required.
Payments happen automatically on every tool call. Configure once, pay per use.
Payments are in USDC on Base (Coinbase's L2). Gas fees are fractions of a cent.
You need an Ethereum wallet with a small USDC balance on Base mainnet.
Option A — New wallet (easiest):
Copy the address and send it $1–5 USDC on Base via Coinbase or bridge.base.org.
Option B — Existing wallet: Export your private key from MetaMask: Account Details → Export Private Key.
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Restart Claude Desktop. The 8 Machina tools will appear automatically.
Once connected, ask Claude:
url_extractscan_pythonvalidate_emaildomain_intelpdf_inspect (free)pdf_extractTestnet mode (free, mock payments):
url_extract)mach402.devThe agent never sees any of this — it just calls a tool and gets a result.
Machina charges per call in USDC on Base mainnet. Payments are settled on-chain via Coinbase CDP. There are no subscriptions, no minimums, no monthly fees.
A $5 USDC balance covers ~1,000 URL extractions or ~250 Python code scans.
MIT
Source: README.md at commit 979eea9
Fetch a URL and return its full content as clean Markdown. Useful for reading web pages, articles, blog posts, and documentation. Returns title, word count, and the full text as Markdown. Cost: $0.005 per call.
urlrequiredScan Python source code for security vulnerabilities. Detects: hardcoded secrets/API keys, eval/exec misuse, shell injection, insecure SSL/TLS, dangerous deserialization (pickle, yaml.load), path traversal, and CVE-affected dependency versions. Returns structured findings with severity (critical/high/medium/low) and line numbers. Handles up to 10,000 lines. Cost: $0.020 per call.
coderequiredfilenameValidate a single email address. Checks: syntax/format, MX record existence, disposable email provider detection, and role-address detection (noreply@, info@, etc.). With smtp_probe=True, attempts an SMTP connection to verify the mailbox exists (best-effort — some servers block probes). Returns a deliverability score and per-check results. Cost: $0.007 per call.
emailrequiredsmtp_probeValidate up to 100 email addresses in a single call. Same checks as validate_email (syntax, MX, disposable, role-address) but optimised for batch processing. SMTP probing is off by default to keep latency low. Returns per-address results plus a summary. Cost: $0.500 per call (up to 100 emails, ~$0.005/email).
emailsrequiredsmtp_probeGet comprehensive intelligence on a domain name. Returns: DNS records (A/MX/NS/TXT/SPF/DMARC), WHOIS registration data and domain age, SSL certificate details and expiry, HTTP response headers, tech stack detection (CMS, server, CDN, etc.), and email infrastructure analysis. Cost: $0.050 per call.
domainrequiredFREE pre-check for a PDF file. Returns page count, file size, and metadata (title, author, creator, creation date) without extracting any text. Use this before pdf_extract or pdf_extract_large to check the page count and decide which extractor to use. No payment required. Cost: FREE.
pdf_pathpdf_base64Extract text from a PDF (up to 50 pages) and return it as Markdown. Preserves headings, tables, lists, and document structure. Call pdf_inspect first to verify page count — use pdf_extract_large for documents over 50 pages. Cost: $0.050 per call.
pdf_pathpdf_base64Extract text from a large PDF (up to 200 pages) and return it as Markdown. For documents over 50 pages. Call pdf_inspect first to check the page count. For documents ≤50 pages, prefer pdf_extract (cheaper). Cost: $0.180 per call.
pdf_pathpdf_base6490% 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.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
gg.machinaOfficial publisher
Remote MCP server giving assistants World Cup 2026 fixtures, team/player context, prediction-market data and model forecasts from Machina Sports.
Published by GitHub account SecondStageTurbine
A remote MCP server where AI agents join research rooms, post cited biomedical findings, review each other's work, and earn reputation.
pip install machina-mcppython -c "from eth_account import Account; a = Account.create(); print('Address:', a.address); print('Key:', a.key.hex())"export MACHINA_WALLET_KEY=0xYOUR_PRIVATE_KEY{ "mcpServers": { "machina": { "command": "machina-mcp", "env": { "MACHINA_WALLET_KEY": "0xYOUR_PRIVATE_KEY" } } }}export MACHINA_NETWORK=eip155:84532export MACHINA_BASE_URL=https://mach402.dev # testnet endpoints at same URL when TESTNET_MODE=true# Test with MCP Inspectornpx @modelcontextprotocol/inspector machina-mcp
# Or run directlyexport MACHINA_WALLET_KEY=0x...machina-mcp