SkillTide Submit
Official description7 sourcesMCP servers8d ago
JessieJanie/skim402

JessieJanie/skim402

Convert any URL into clean Markdown with structured
View on GitHub ↗Direct link · no redirect page
Config template (adjust for your client)
claude mcp add skim402 -- npx -y skim402
A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.
Star count
3 ★ · JessieJanie/skim402 · read from the GitHub search API · (checked 2026-10-16 20:00:20)
Source
collected from the punkpeye/awesome-mcp-servers list · type: MCP server
Harvest history
first seen 2026-10-09 · last seen 2026-10-16 · seen 32× · listed by 7 sources
Score
score 703 · 3 ★ · 7 sources · mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository JessieJanie/skim402;first catalogued 2026-10-09;last seen 2026-10-16。There is no official certification or quality rating here — we record sources and dates only.
Third-party quality signals

Claude plugin users

以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →

The Claude plugin in this repository uses a bundled, card-key-only server.
It does not run the npm/wallet setup below. See CLAUDE-PLUGIN.md
for installation, data handling, credit costs, and reviewer checks.
---
skim-mcp
**Skim is the complete web toolkit for AI agents—not just a simple page reader. Get a free card key at skim402.com/pricing; wallet/x402 is optional.**
skim-mcp is the official Model Context Protocol server for Skim. It turns public pages into clean, agent-ready Markdown—typically ~4x smaller than raw HTML in Skim's measured comparisons—and exposes the full toolkit: clean reads, batch reads, JavaScript/browser rendering, structured extraction, crawling, PDFs, page-change watches, and curated Signals.
**Default path: a card-plan API key.** Get a free sk402_ key at skim402.com (pricing). Paste it as SKIM_API_KEY. A crypto wallet is **not** required.
**Optional path: x402 wallet pay.** If you prefer pay-per-call in USDC on Base, you can set SKIM_WALLET_PRIVATE_KEY instead. Ignore this unless you want it.
**Tools in this package:** read_url, read_urls, extract_url, crawl_url, read_pdf, watch_urls, check_watch, poll_signal.
> **Try before you integrate:** use the Playground for a quick read or the Workbench to test batches, extraction, crawl, PDFs, watches, and Signals.
---
Quickstart (60 seconds)
Card API key (recommended)
**1.** Get a free key at **skim402.com** — it starts with sk402_. Card required at signup; 1,000 reads/month on the free plan. Details: skim402.com/pricing.
**2.** Add this to your MCP client. **Claude Desktop** — ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows). **Cursor** — ~/.cursor/mcp.json (or **Settings → MCP**). Same JSON works in Cline, Continue, Zed, and other MCP clients:
**3.** Restart the client and ask it to read a URL:
---
Wallet / x402 (optional)
Only if you prefer pay-per-call ($0.002 USDC on Base) instead of a card key. You can skip this entire block.
Fund a **dedicated** Base wallet with a small USDC balance ($1 ≈ 500 reads). Setup guide: ** **.
> **Use a fresh wallet, not your personal one.** This private key lives in a plaintext config file on your machine — treat it like a hot wallet for $0.002 tolls, not a savings account.
---
FAQ
**Do I need an API key?**
Yes for the default path. Get a free sk402_ key at https://skim402.com. A wallet is optional.
**Is this wallet-only? Do I need crypto?**
No. Card API key is the default. x402 wallet pay is optional.
**What tools can my agent call?**
read_url, read_urls (batch), extract_url, crawl_url, read_pdf, watch_urls, check_watch, and poll_signal.
---
Try it without an agent
With a card key:
Wallet / x402 challenge (optional — returns HTTP 402 if you send no payment):
---
The tools
read_url
Reads any URL and returns clean Markdown with a YAML frontmatter block.
**Input:** { "url": "https://example.com/article" }
**Routes:** GET /api/t/read?url= (API key) · POST /api/v1/read (wallet)
**Output:**
read_urls
Batch-read 1–10 URLs in one call. Optional stripLinks / stripImages.
**Input:** { "urls": ["https://a.example", "https://b.example"] }
**Routes:** POST /api/t/read/batch · POST /api/v1/read/batch
extract_url
Structured JSON from a page. Pass a JSON Schema, or a preset: article, product, job, review, event, table.
**Input:** { "url": "https://example.com/product", "preset": "product" }
**Routes:** POST /api/t/extract · POST /api/v1/extract
Presets are sent as schemas on those extract routes.
crawl_url
Crawl a site (origin or start URL) and return clean Markdown per page. Discovers sitemap.xml / robots.txt sitemaps plus same-origin links. Cap 25 pages. **1 credit per successful page**; failed pages are not charged.
Source
awesome · https://github.com/JessieJanie/skim402
Browse by field
MCP servers
Traction
3 ★
added
yesterday

More in MCP servers

All 5,525 in MCP servers →

Filed under

Every tag opens the full list for that filter. Counts are the live catalogue figures.

Browse all fields →

← Back to index