pagewire
Turn public web pages into clean Markdown and structured metadata, paid per call in USDC with a daily free allowance.
Fetch one public page and get its title, description, clean Markdown, and links (
page_to_markdown, $0.01).Extract page metadata: title, description, canonical URL, language, OpenGraph/Twitter cards, icons, JSON-LD (
page_metadata, $0.005).Read a page plus up to 4 same-host linked pages as Markdown, with optional path prefix filter (
crawl_site, $0.03).Use plain HTTP fetch (no JavaScript rendering, 15 s timeout, first 2 MB only); deterministic, no model calls.
Pay per call via x402 in USDC on Base or Solana; no API key or account, first $0.10 per client per day free.
Bad inputs or fetch errors (non-public URL, HTTP error, timeout, non-text) return
isErrorand are never charged.Connect via stdio bridge or directly to
https://pagewire.dev/mcp; also plain HTTP endpoints for extract/meta/crawl.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pagewire fetch https://example.com/blog/post as clean markdown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pagewire-mcp
🤖 Built by the makers of Agent!, an autonomous macOS agent. 🌐 agentiloop.ai
MCP server for PageWire. It turns any public web page into clean Markdown for AI agents, paid per call in USDC. There is no API key and no account.
Try it free: tool calls without payment are free up to $0.10 of list price per client per day (10 pages to Markdown, 20 metadata calls or 3 crawls). After that the tool answers with an x402 payment request.
Tool | What it does | Price |
| Fetches a public page and returns its title, description, clean Markdown and links. Deterministic, no model call | $0.01 |
| Returns title, description, canonical URL, language, OpenGraph and Twitter cards, icons and JSON-LD | $0.005 |
| Reads a page plus up to 4 same-site pages it links to (optionally only under a path | $0.03 |
This package is a dependency-free stdio bridge (Node 18+) to the hosted Streamable-HTTP server at https://pagewire.dev/mcp. Clients that speak Streamable HTTP can use that URL directly and skip the bridge.
Install
Claude Code
claude mcp add pagewire -- npx -y github:AgentiLoop/pagewire-mcp
# or, without the bridge:
claude mcp add --transport http pagewire https://pagewire.dev/mcpClaude Desktop / Cursor / Windsurf / Cline (stdio)
{ "mcpServers": { "pagewire": { "command": "npx", "args": ["-y", "github:AgentiLoop/pagewire-mcp"] } } }Any Streamable-HTTP client
{ "mcpServers": { "pagewire": { "type": "http", "url": "https://pagewire.dev/mcp" } } }Verify
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | npx -y github:AgentiLoop/pagewire-mcpRelated MCP server: x402-md-mcp
Paying
Within the daily free allowance a tool call just works; the result's
_meta["pagewire/free"]shows the allowance left today.After that, a call without payment returns
isError: truewithstructuredContentset to the x402 v2 PaymentRequired object (theacceptslist: network, asset, amount,payTo), following the x402 MCP transport.@x402/mcpclients pay automatically.To pay by hand, sign one
acceptsentry with any x402 client and call the tool again with the payload inparams._meta["x402/payment"](or the base64 payload as thepaymentargument).A bad input or a page that cannot be fetched (4xx) is never charged.
The same tools are plain HTTP endpoints: GET https://pagewire.dev/x402/extract?url=…, /x402/meta?url=… and /x402/crawl?url=…. Each one also accepts MPP (npx mppx "https://pagewire.dev/x402/extract?url=https://example.com"). Discovery: openapi.json, llms.txt.
Environment
Variable | Default |
|
|
|
|
Official MCP registry entry: dev.pagewire/web. Agent skill: npx skills add https://pagewire.dev.
License
MIT. The bridge is open source; the hosted service is at https://pagewire.dev/.
Available Tools
3 toolscrawl_siteRead a page + 4 linked pages ($0.03/call)ARead-only
Fetch a public web page plus up to 4 pages on the same host that it links to (in link order, or only those whose path starts with prefix), and return each one as title + clean Markdown. Good for reading a docs section or a small site in one call. No model call, deterministic. For a single page use page_to_markdown (cheaper), for metadata only use page_metadata. Plain HTTP fetch (no JavaScript rendering, 15 s timeout, only the first 2 MB is read). Errors (non-public URL, upstream HTTP error, timeout, non-text content) return isError with the reason and are never charged. Price: $0.03 USDC per call via x402 (USDC on Base or Solana, no account; nothing is charged for a bad input). First $0.1 of calls per day per client are free (no payment needed).
Inputs: url (required), limit, prefix, payment.
page_metadataWeb page metadata ($0.005/call)ARead-only
Fetch a public web page and return its metadata: title, description, canonical URL, language, OpenGraph and Twitter card tags, icons and parsed JSON-LD blocks. Use it for link previews, SEO checks or structured data (JSON-LD) without the page body; use page_to_markdown when you need the readable text and links. Plain HTTP fetch (no JavaScript rendering, 15 s timeout, only the first 2 MB is read). Errors (non-public URL, upstream HTTP error, timeout, non-text content) return isError with the reason and are never charged. Price: $0.005 USDC per call via x402 (USDC on Base or Solana, no account; nothing is charged for a bad input). First $0.1 of calls per day per client are free (no payment needed).
Inputs: url (required), payment.
page_to_markdownWeb page → Markdown ($0.01/call)ARead-only
Fetch a public web page and return its title, description, clean Markdown (scripts, styles, nav chrome removed) and the list of links. No model call, deterministic. Use it to read the content of one page; use page_metadata if you only need title/OpenGraph/JSON-LD (cheaper), or crawl_site to read the page plus the pages it links to in one call. Plain HTTP fetch (no JavaScript rendering, 15 s timeout, only the first 2 MB is read). Errors (non-public URL, upstream HTTP error, timeout, non-text content) return isError with the reason and are never charged. Price: $0.01 USDC per call via x402 (USDC on Base or Solana, no account; nothing is charged for a bad input). First $0.1 of calls per day per client are free (no payment needed).
Inputs: url (required), payment.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct output: clean Markdown body, metadata/JSON-LD only, or a multi-page crawl. The descriptions explicitly cross-reference each other ("use page_metadata if you only need title...", "use crawl_site to read the page plus the pages it links to"), leaving no real ambiguity about selection.
All names are snake_case with a consistent noun/verb structure (page_to_markdown, page_metadata, crawl_site), and the two 'page' tools share a clear prefix. The 'crawl_' verb on the third tool is a minor deviation from the 'page_' prefix pattern but remains readable and descriptive.
Three tools is well scoped for a page-fetching service, and each one earns its place by covering a genuinely different retrieval mode (full body, metadata only, small crawl). No redundant or filler tools.
The surface covers the core fetch lifecycle: single-page content, lightweight metadata, and same-host multi-page crawling, with clear error and pricing semantics. Minor gaps remain around cross-host or larger batch fetching and deeper crawl controls (e.g. page limits, sitemap), but agents can work around these with repeated calls.
Related MCP Connectors
Web pages to Markdown, metadata and small crawls for agents. Free daily calls, then USDC x402/MPP.
Turn any public web page into clean Markdown. Pay-per-call via x402: 0.005 USDC on Base.
Pay-per-request webpage-to-Markdown extraction for AI agents. $0.005 USDC via x402 on Solana.
Fetch any URL as clean Markdown or metadata, and buy digital goods via x402 — for AI agents.
Related MCP Servers
- AlicenseAqualityCmaintenancePay-per-use clean web reader for AI agents. URL in, markdown plus metadata out, in milliseconds. Settled per-call in USDC over x402 — no signup, no API keys.1102 npm3MIT
- AlicenseNot gradedqualityDmaintenanceEnables extracting clean Markdown from any webpage by paying $0.005 USDC per call via the x402 protocol, with automatic wallet-based payment settlement.10 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to reliably fetch public web URLs and extract clean, agent-ready text, Markdown, links, and metadata, with automatic browser fallback and optional x402 payment support.-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents and MCP clients to inspect a URL for reachability, then extract clean structured Markdown, headings, and links from public web pages, paid per successful request via x402 micropayments with no accounts or API keys.MIT