HTML/CSS to Image API

io.github.htmlcsstoimage由 GitHub 帳號 htmlcsstoimage 發布v1.1.0更新於 Oct 24, 2026

Generate images and PDFs from HTML/CSS, live websites, and reusable templates.

已驗證Streamable HTTP可網頁執行瀏覽器自動化媒體與設計

概覽

AI 產生的概覽

託管式 HCTI MCP 伺服器，讓助理把 HTML/CSS、即時網頁與範本渲染成圖片或 PDF。

可以做什麼
  • 將 HTML/CSS 渲染為圖片或 PDF，並擷取公開網址或指定頁面元素
  • 以變數值渲染已儲存的範本，建立與更新範本，列出範本及其版本紀錄
  • 一次批次產生多張圖片變體，並查詢帳戶的批次上限
  • 管理網站的動態 Open Graph 圖片設定
  • 管理 HCTI 存取來源網站所用的代理，以及生成圖片的外部儲存目的地
  • 查詢所屬組織的圖片用量與上限
適用情境
適合需要產生社群卡片、Open Graph 預覽圖、即時網頁截圖，或把標記輸出成圖片／PDF 而不自行執行瀏覽器的情境，也適合以範本重複渲染。
執行需求
透過瀏覽器 OAuth 連線至 mcp.hcti.io 的遠端 Streamable HTTP 端點，不需 API 金鑰或本機安裝。渲染需要 HCTI 帳戶並有可用額度。
安裝前請注意
渲染會消耗 HCTI 額度且需要帳戶。HTML、CSS、範本變數、目標網址與資源設定會傳送至託管服務，持續性資源保存在所連線的組織中；請勿傳入 cookie、授權標頭或私有網址。建立、更新、刪除類工具會變更帳戶，且 update_og_config 會整份取代設定。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 HTML/CSS to Image API，將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.htmlcsstoimage%2Fhtml-css-to-image/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "html-css-to-image-api": {
      "type": "http",
      "url": "https://mcp.hcti.io/"
    }
  }
}

README

HTML/CSS to Image API for AI agents

Let AI agents capture live website screenshots, render HTML/CSS, and populate reusable templates as images or PDFs—without managing a browser.

This repository is a portable Agent Plugin package with client-specific manifests for the hosted HCTI MCP server at https://mcp.hcti.io. Authentication uses HCTI's browser-based OAuth flow; no API key or access token is stored in this repository.

Repository layout

PathPurpose
plugin.jsonPortable Agent Plugins manifest.
mcp.jsonPortable MCP configuration.
.mcp.jsonClaude Code, GitHub Copilot, and Grok-compatible MCP configuration.
llms-install.mdAgent-readable installation guidance for Cline and other MCP clients.
.codex-plugin/plugin.jsonNative ChatGPT and Codex plugin manifest.
.app.jsonMaps the package to the official published OpenAI plugin.
.claude-plugin/plugin.jsonClaude Code plugin manifest.
.cursor-plugin/plugin.jsonCursor Marketplace manifest.
.grok-plugin/plugin.jsonGrok Build marketplace manifest.
gemini-extension.jsonGemini CLI extension manifest.
kimi.plugin.jsonKimi Code plugin manifest.
skills/hcti-image-generation/Image generation and template workflow guidance.
skills/hcti-open-graph-images/Dynamic Open Graph image configuration guidance.
clawhub/html-css-to-image/Standalone OAuth/MCP rendering skill for ClawHub.
clawhub/hcti-open-graph-images/Standalone OAuth/MCP Open Graph skill for ClawHub.

ChatGPT and Codex

Install the official HTML/CSS to Image plugin from the Plugins Directory in ChatGPT or Codex. This is the preferred OpenAI integration and uses HCTI's registered MCP connection with browser-based OAuth.

The native .codex-plugin/plugin.json manifest packages the shared HCTI skill, while .app.json maps the package to the published OpenAI plugin.

Kimi Code

Install the plugin directly from GitHub in Kimi Code:

text
/plugins install https://github.com/htmlcsstoimage/agent-plugins/reload

Run /mcp-config login hcti and complete authorization in your browser. Then use /mcp to confirm that the HCTI tools are connected.

To test a local checkout, use /plugins install /path/to/agent-plugins. Kimi copies installed plugins into its managed plugin directory, so reinstall after changing the local source.

Gemini CLI

Install the extension directly from GitHub:

bash
gemini extensions install https://github.com/htmlcsstoimage/agent-plugins

Restart Gemini CLI, run /extensions list to confirm the extension is enabled, then run /mcp auth hcti and complete authorization in your browser. Use /mcp list to confirm the HCTI tools are connected. Gemini CLI automatically discovers the included HCTI Agent Skills.

To test a local checkout during development, run gemini extensions link /path/to/agent-plugins, restart Gemini CLI, and inspect it with /extensions list.

GitHub Copilot

Install a local checkout

Install this repository directly:

bash
copilot plugin install /path/to/agent-plugins

Start Copilot CLI and use /plugin list, /skills list, and /mcp to confirm that the plugin, skill, and HCTI server are available. Connect hcti from /mcp and complete authorization in your browser.

Cline

Give Cline the repository's llms-install.md to configure the hosted HCTI server, or add it manually as a remote Streamable HTTP server at https://mcp.hcti.io. Complete the OAuth authorization in your browser; no API key or local server installation is required.

Claude Code

Install from the Claude community marketplace

After the plugin is published, add Anthropic's community marketplace and install the plugin:

text
/plugin marketplace add anthropics/claude-plugins-community/plugin install html-css-to-image@claude-community/reload-plugins

Run /mcp, select hcti, and complete authorization in your browser. Claude can invoke the HCTI skill automatically when relevant; it is also available as /html-css-to-image:hcti-image-generation.

Test a local checkout

Validate and load this repository directly:

bash
claude plugin validate . --strictclaude --plugin-dir .

In the test session, run /mcp to connect hcti, then try an image request. Use /reload-plugins after changing the manifest, skill, or MCP configuration.

Cursor

Install from the Cursor Marketplace

After the plugin is published, open Customize in Cursor, search for HTML/CSS to Image API, select Install, and choose the desired scope.

Open Cursor's MCP settings, find hcti, select Connect, and complete authorization in your browser. Start a new Agent chat after connecting so the HCTI tools are available.

Test a local checkout

Copy this repository into Cursor's local plugin directory:

bash
mkdir -p ~/.cursor/plugins/localcp -R /path/to/agent-plugins ~/.cursor/plugins/local/html-css-to-image

Restart Cursor or run Developer: Reload Window, then confirm that HTML/CSS to Image API appears in Customize. Connect the hcti MCP server from Cursor's MCP settings before testing an image request.

For another test cycle, replace the copied html-css-to-image directory with the current checkout and reload Cursor.

Grok Build

The xAI plugin marketplace points to this repository at a pinned commit. Its Grok manifest reuses the root skill, MCP endpoint, and assets.

After the marketplace entry is available, install HTML/CSS to Image in Grok Build, connect the hcti MCP server when prompted, and complete authorization in your browser.

ClawHub / OpenClaw

The ClawHub skill supports HTML/CSS rendering, website screenshots, PDF output, and saved-template rendering through the hosted MCP server. Users connect to https://mcp.hcti.io using browser-based OAuth; no API keys are required. Rendering requires an HCTI account and available credits.

The separate Open Graph skill creates persistent dynamic social-preview configurations and integrates their image URLs into website metadata. It includes the webpage integration reference and uses the same OAuth connection.

These standalone distributions live outside skills/ so other clients do not discover duplicate skills. Their setup instructions register the server in OpenClaw and complete OAuth; installing a skill alone does not establish the connection. Publish only the skill folder, not the whole plugin repository.

From this repository's root, with the current ClawHub CLI installed:

bash
clawhub loginclawhub skill publish ./clawhub/html-css-to-image \  --slug html-css-to-image \  --name "HTML/CSS to Image" \  --categories integrations,creative \  --topics "screenshots,html,css,pdf,images" \  --dry-run

Preview the Open Graph skill separately:

bash
clawhub skill publish ./clawhub/hcti-open-graph-images \  --slug hcti-open-graph-images \  --name "HTML/CSS to Image — Dynamic Open Graph Images" \  --categories integrations,development \  --topics "open-graph,social-previews,seo,images,html" \  --dry-run

After reviewing each preview, run its publish command without --dry-run. To publish under an organization, add --owner <your-clawhub-owner-handle> to both commands; otherwise the authenticated user owns the listing. Publication is separate from committing this repository, and new releases may wait for automated review.

ClawHub distributes published skills under MIT-0. Review those terms before the first publication; the hosted HCTI service remains subject to its own terms. See ClawHub publishing and skill format.

Included capabilities

The core rendering and template tools are:

ToolPurpose
create_imageRender HTML and CSS as an image or PDF.
create_url_imageCapture a public URL or selected page element.
create_templated_imageRender a saved HCTI template with variable values.
create_batch_imagesGenerate multiple image variations in one request.
get_max_batch_sizeCheck the account's current batch limit.
create_templateSave a reusable HTML/CSS template.
update_templateUpdate an existing template.
list_templatesList templates in the authorized account.
list_template_versionsInspect a template's version history.

Managing resources with MCP

Beyond generating images, the HCTI MCP server can manage supporting resources in the connected organization:

ResourceToolsPurpose
Usagecheck_usageCheck the organization's current image usage and limits.
Open Graph configurationscreate_og_config, update_og_config, get_og_config, list_og_configs, delete_og_configManage dynamic social-preview images for pages on a website.
Proxiescreate_proxy, update_proxy, get_proxy, list_proxies, delete_proxyManage proxies used when HCTI accesses source websites.
Storage destinationscreate_storage_destination, update_storage_destination, get_storage_destination, list_storage_destinations, delete_storage_destination, get_aws_storage_external_idManage external destinations for generated images and retrieve the external ID needed for AWS setup.

Dynamic Open Graph image configurations are an especially useful integration point. An agent can resolve an existing HCTI template, map page metadata into its variables, optionally select a configured proxy or storage destination, and create a persistent configuration for serving cached social images.

Resource tools operate on the HCTI organization selected during OAuth authorization, and available tools depend on the permissions granted to that connection. Listing and retrieval are read-only; create, update, and delete operations change the account. In particular, update_og_config replaces the complete configuration, so agents should retrieve the current configuration and preserve unchanged settings before updating it.

Example requests

  • "Create a 1200×630 Open Graph image with this title and color palette."
  • "Capture the pricing table on https://example.com/pricing."
  • "List my HCTI templates and render the social-card template with this headline."
  • "Create five product-card variations with different accent colors."
  • "Create a dynamic Open Graph configuration for https://example.com using my social-card template and map its title and description from page metadata."

Data handling

Requests sent through the plugin are processed by the hosted HTML/CSS to Image service. HTML, CSS, template values, target URLs, rendering options, and resource configuration supplied to HCTI are sent to that service; persistent resources are stored in the connected HCTI organization. Do not provide cookies, authorization headers, private URLs, or other secrets unless intentionally configuring an authorized rendering workflow and you understand that HCTI will process that data.

License and service terms

The plugin files in this repository are available under the MIT License. The license applies to this repository's source code, configuration, and documentation; it does not license the hosted HTML/CSS to Image service. Use of the service is governed separately by the Terms of Use and Privacy Policy.

Validate

Run the repository checks:

bash
node scripts/validate-template.mjs

Validate the Claude adapter with Claude Code's official strict validator:

bash
claude plugin validate . --strict

Verified compatibility

The plugin runtime, shared HCTI skills, MCP discovery, and browser-based OAuth flow were tested with Claude Code 2.1.258. Use Claude Code 2.1.281 or newer for strict validation of directory listing metadata such as privacyPolicyUrl.

The Grok adapter is validated by the xAI marketplace's catalog and component-index checks against the pinned commit.

HOL Registry

Our AI agent plugins are registered in the HOL Plugin Registry, where you can review installation details, security findings, provenance, and the current trust score.

[HTML/CSS to Image API trust badge]

Documentation and support

來源：README.md，提交 73eb09e

工具

0
該伺服器需要登入，因此 SourceWeft 無法在沒有帳號的情況下讀取其工具，也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

2
  1. v1.1.0最新Oct 5, 2026
  2. v1.0.2Sep 16, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分