Skip to content
Back to search

sitemcp

Fetch an entire site and use it as an MCP Server

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ryoppippi--sitemcp/badge.svg)](/listings/ryoppippi--sitemcp)

HTML

<a href="/listings/ryoppippi--sitemcp"><img src="/api/listings/ryoppippi--sitemcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

One-off usage (choose one of the followings):

bunx sitemcp
npx sitemcp
pnpx sitemcp

Install globally (choose one of the followings):

bun i -g sitemcp
npm i -g sitemcp
pnpm i -g sitemcp

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 160 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # SiteMCP
  2. > [!WARNING]
  3. > **This repository is archived.** Please read the notice below before using this project.
  4. ## Archival Notice
  5. SiteMCP was created on 8 April 2025, in the very early days of the Model Context Protocol ([original tweet](https://x.com/ryoppippi/status/1909369320078999673), [introduction post, Japanese](https://ryoppippi.com/blog/2025-04-08-zenn-1eb7fbe9042a88-ja)). At the time, MCP was a brand-new concept, and passing documentation to AI assistants via an MCP server was one of the only practical options available. Claude Code was exclusively available under a usage-based plan and had not yet reached wide adoption — and features like skills did not yet exist. (For that reason, all the demos in this repository were recorded with Claude Code Desktop.)
  6. Back then, coding agents were far less capable and LLM-native web search was unreliable at best, so fetching an entire website and serving it through MCP was genuinely useful. SiteMCP was arguably one of the earliest and most practical ways to provide documentation to a local AI assistant.
  7. The landscape has since changed significantly. MCP itself went through a period of rapid growth followed by a correction, and the community converged on simpler, more efficient alternatives for static documentation: publishing docs as downloadable Markdown files, distributing them via npm packages, or falling back to web search as a last resort. In my view, using MCP to serve static documentation has become an anti-pattern — the overhead is simply not worth it. I wrote about this in detail on my blog:
  8. - [Why You Should Publish Docs on npm (English)](https://ryoppippi.com/blog/2025-12-14-publish-docs-on-npm-en)
  9. - [Why You Should Publish Docs on npm (Japanese)](https://ryoppippi.com/blog/2025-12-14-publish-docs-on-npm-ja)
  10. One year after its initial release, I have decided to archive SiteMCP. If you need to provide documentation to an AI assistant, please follow the guidance in my blog posts above and fetch documentation as statically as possible.
  11. ---
  12. [![npm version](https://img.shields.io/npm/v/sitemcp?color=yellow)](https://npmjs.com/package/sitemcp)
  13. [![NPM Downloads](https://img.shields.io/npm/dy/sitemcp)](https://tanstack.com/stats/npm?packageGroups=%5B%7B%22packages%22:%5B%7B%22name%22:%22sitemcp%22%7D%5D%7D%5D&range=30-days&transform=none&binType=daily&showDataMode=all&height=400)
  14. [![DeepWiki](https://img.shields.io/badge/DeepWiki-ryoppippi%2Fsitemcp-blue.svg?logo=data:image/png;base64,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)](https://deepwiki.com/ryoppippi/sitemcp)
  15. Fetch an entire site and use it as an MCP Server
  16. https://github.com/user-attachments/assets/ebe2d7c6-4ddc-4a37-8e1e-d80fac49d8ae
  17. <details>
  18. <summary><bold>Demo in Japanese</bold></summary>
  19. https://github.com/user-attachments/assets/24288140-be2a-416c-9e7c-c49be056a373
  20. </details>
  21. > [!NOTE]
  22. > `sitemcp` is a fork of [`sitefetch`](https://github.com/egoist/sitefetch) by [@egoist](https://github.com/egoist)
  23. ## Install
  24. One-off usage (choose one of the followings):
  25. ```bash
  26. bunx sitemcp
  27. npx sitemcp
  28. pnpx sitemcp
  29. ```
  30. Install globally (choose one of the followings):
  31. ```bash
  32. bun i -g sitemcp
  33. npm i -g sitemcp
  34. pnpm i -g sitemcp
  35. ```
  36. ## Usage
  37. ```bash
  38. sitemcp https://daisyui.com
  39. # or better concurrency
  40. sitemcp https://daisyui.com --concurrency 10
  41. ```
  42. ### Tool Name Strategy
  43. Use `-t, --tool-name-strategy` to specify the tool name strategy, it will be used as the MCP server name (default: `domain`).
  44. This will be used as the MCP server name.
  45. ```bash
  46. sitemcp https://vite.dev -t domain # indexOfVite / getDocumentOfVite
  47. sitemcp https://react-tweet.vercel.app/ -t subdomain # indexOfReactTweet / getDocumentOfReactTweet
  48. sitemcp https://ryoppippi.github.io/vite-plugin-favicons/ -t pathname # indexOfVitePluginFavicons / getDocumentOfVitePluginFavicons
  49. ```
  50. ### Max Length of Content
  51. Use `-l, --max-length` to specify the max length of content, default is `2000` characters.
  52. This is useful for sites with long content, such as blogs or documentation.
  53. The acceptable content length depends on the MCP client you are using, so please check the documentation of your MCP client for more details.
  54. Also welcome to open an issue if you have any questions.
  55. ```bash
  56. sitemcp https://vite.dev -l 10000
  57. ```
  58. ### Match specific pages
  59. Use the `-m, --match` flag to specify the pages you want to fetch:
  60. ```bash
  61. sitemcp https://vite.dev -m "/blog/**" -m "/guide/**"
  62. ```
  63. The match pattern is tested against the pathname of target pages, powered by micromatch, you can check out all the supported [matching features](https://github.com/micromatch/micromatch#matching-features).
  64. ### Content selector
  65. We use [mozilla/readability](https://github.com/mozilla/readability) to extract readable content from the web page, but on some pages it might return irrelevant contents, in this case you can specify a CSS selector so we know where to find the readable content:
  66. ```sitemcp
  67. sitemcp https://vite.dev --content-selector ".content"
  68. ```
  69. ## How to configure with MCP Client
  70. You can execute server from your MCP client (e.g. Claude Desktop).
  71. The below example configuration for Claude Desktop
  72. ```json
  73. {
  74. "mcpServers": {
  75. "daisy-ui": {
  76. "command": "npx",
  77. "args": [
  78. "-y",
  79. "sitemcp",
  80. "https://daisyui.com",
  81. "-m",
  82. "/components/**"
  83. ]
  84. }
  85. }
  86. }
  87. ```
  88. ## Tips
  89. - Some site has a lot of pages. It is better to run `sitemcp` before registering the server to the MCP client. `sitemcp` caches the pages in `~/.cache/sitemcp` by default. You can disable by `--no-cache` flag.
  90. ## License
  91. MIT.
  92. ## Sponsors
  93. <!-- spellchecker:disable-line -->
  94. <p align="center">
  95. <a href="https://github.com/sponsors/ryoppippi">
  96. <img src="https://cdn.jsdelivr.net/gh/ryoppippi/sponsors@main/sponsors.svg">
  97. </a>
  98. </p>
  99. ## Stats
  100. <a href="https://www.star-history.com/#ryoppippi/sitemcp&Date">
  101. <picture>
  102. <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=ryoppippi/sitemcp&type=Date&theme=dark" />
  103. <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=ryoppippi/sitemcp&type=Date" />
  104. <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=ryoppippi/sitemcp&type=Date" />
  105. </picture>
  106. </a>
  107. ![Stats by Repobeats](https://repobeats.axiom.co/api/embed/2ad989875810c346a80fa4677ed0154ef94132c3.svg "Repobeats analytics image")

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.