MCP.Market

CleanPage MCP server

online · 100% uptime
by IO31-WEB·io.github.IO31-WEB/cleanpage·v1.0.0

Turn any URL into clean, structured, agent-ready content. $0.02/call via x402 on Base.

A88/100grade A
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed CleanPage yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

CleanPage tools (4)

write = sends, deletes, buys or posts
  • clean_pageFree

    Fetches a URL and returns clean, structured, agent-optimized content: readable markdown, plain text, metadata (author/date/site/word count), extracted links and images, an optional structured facts array, and a 0-100 quality score. Handles common failure modes (paywalls, bot-walls, empty JS shells) with clear typed errors instead of silently returning junk. PAID TOOL: $0.02 USDC per successful call via x402 (USDC on base). Call with no payment first to receive the exact payment requirements (HTTP 402), then retry with an X-PAYMENT header. Failed extractions are not charged.

  • healthFree

    Free. Returns service status, version, and uptime signal. Use to check the service is reachable before paying for anything.

  • list_capabilitiesFree

    Free. Returns the full list of tools this server offers, including which are paid, their prices, and their input schemas — so an agent can decide what to call before spending anything.

  • pricingFree

    Free. Returns current pricing, accepted payment network/asset, and the x402 payment flow details for paid tools.

Public scan report

scanner v0.1.10 · 2026-10-02 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 728ms20/20
  • Tool poisoning4 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 14 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How CleanPage compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 80% of 4,460 AI and agents servers
Tools
4
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
109 ms
faster than 84% of 2,331 AI and agents servers

What its tools let an agent do: 4 read

Install CleanPage in Claude Code, Cursor or VS Code

claude mcp add --transport http cleanpage https://cleanpage-mcp.cleanpage-mcp.workers.dev/mcp
Add to Cursor

What the publisher says

From the CleanPage repository's README, as published. We do not edit it. Read it on GitHub

CleanPage

A paid MCP tool that turns any URL into clean, structured, agent-optimized content. Agents pay $0.02 USDC per successful call via x402 on Base — no accounts, no API keys, no subscriptions.

clean_page(url) → { title, clean_markdown, plain_text, structured_facts,
                     metadata, links, images, quality_score, extraction_notes }

Built for Cloudflare Workers. Full TypeScript. No paid infra required beyond a domain and a Base wallet address.

How agents use this

  1. Discover the service for free — no payment needed for any of this:
  • GET /.well-known/agent.json — machine-readable capability card
  • GET /.well-known/mcp.json — MCP connection + pricing manifest
  • GET /llms.txt — plain-text summary for LLM crawlers
  • MCP tools health, list_capabilities, pricing (all free)
  1. Connect an MCP client to https:///mcp over Streamable HTTP:
{
     "mcpServers": {
       "cleanpage": { "url": "https://<your-domain>/mcp", "transport": "streamable-http" }
     }
   }
  1. Call cleanpage** with no payment attached first:
POST /mcp
   { "jsonrpc": "2.0", "id": 1, "method": "tools/call",
     "params": { "name": "clean_page", "arguments": { "url": "https://example.com/article" } } }

The response is HTTP 402 with an accepts array describing exactly what payment is required (amount, network, asset, payee address).

  1. Sign and retry. Construct a USDC transferWithAuthorization (EIP-3009) payment payload for the requested amount, base64-encode it, and retry the same request with an X-PAYMENT header. Most x402 client libraries (e.g. x402-fetch, x402-axios) do steps 3–4 for you automatically.
  1. Get the result. On success, the response carries the full JSON result plus an X-PAYMENT-RESPONSE header with the settlement transaction hash. Failed extractions (paywalls, bot-blocks, empty pages) are never charged — settlement only happens after a successful extraction.

Full protocol details: see /llms.txt and /.well-known/mcp.json once deployed, or the "For agents" section of the landing page.

Project structure

cleanpage/
├── src/
│   ├── index.ts                # Hono app: routes, x402 payment gate, static asset fallback
│   ├── types.ts                # Shared types (Env, CleanPageResult, etc.)
│   ├── config.ts                # Reads env vars into a typed config object
│   ├── mcp/
│   │   ├── server.ts            # JSON-RPC 2.0 / MCP method dispatcher (stateless)
│   │   └── tools.ts             # Tool schemas + descriptions (clean_page, health, ...)
│   ├── extraction/
│   │   ├── extractor.ts         # Core pipeline: fetch → Readability → markdown/links/metadata
│   │   └── enrichment.ts        # Optional cheap LLM pass for structured_facts
│   ├── payments/
│   │   └── x402.ts              # x402 payment requirements, facilitator verify/settle
│   └── middleware/
│       └── limits.ts            # KV-backed rate limiting + call/revenue analytics
├── public/                       # Static assets served at the Worker's root
│   ├── index.html                # Landing page (live demo, pricing, docs, for-agents)
│   ├── robots.txt                 # Explicitly welcomes agent/LLM crawlers
│   ├── llms.txt                   # Plain-text agent-facing summary
│   └── .well-known/
│       ├─

Architecture notes

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

CleanPage: common questions

Is CleanPage MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the CleanPage safety report
How do I install CleanPage?
It runs remotely at cleanpage-mcp.cleanpage-mcp.workers.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does CleanPage need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is CleanPage maintained?
The last commit was 47 days ago (2026-09-18). The latest release is v1.0.0.
Is CleanPage up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of CleanPage?
Servers from other publishers that do the same job: Agent-Native Plan MCP server, IWE (iwe.md) MCP server and Agoragentic Agent OS MCP server.
How does CleanPage compare with other AI and agents MCP servers?
safety score 88/100 (higher than 80% of 4,460 AI and agents servers); tools 4 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to CleanPage

Same job from other publishers: the closest match first, then the best rated.

  • Agent-Native Plan
    Structured visual plans and PR recaps with diagrams, prototypes, annotations, and sharing
    A
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Agoragentic Agent OS MCP
    Triptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.
    B
  • DataSinking
    Full-text financial reports (US, China, Japan, Korea, Taiwan, UK) as clean Markdown for RAG agents.
    A
  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    A