Skillforge Render API
Screenshot, PDF, OG-image, and page extraction (markdown/JSON) over MCP. Bearer key or x402.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"render-api": {
"url": "https://render.skillforge99.com/mcp"
}
}
}リモートエンドポイント
https://render.skillforge99.com/mcpstreamable-httpできること
ツール一覧
ツール（4）
🟢screenshot_url(url, html, width, height, fullPage, ...)
Capture a screenshot image of a public web page or an inline HTML snippet, rendered in a real headless browser (JS, CSS, and web fonts execute). Returns a PNG/JPEG/WEBP image. Use this to visually preview a page, generate a thumbnail, or archive how a URL looked at a point in time.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public http(s) URL to screenshot (exactly one of url/html)"
},
"html": {
"type": "string",
"description": "Raw HTML to render (exactly one of url/html, max 1MB)"
},
"width": {
"type": "number",
"description": "Viewport width in pixels, 320-1920 (default 1280)"
},
"height": {
"type": "number",
"description": "Viewport height in pixels, 240-1080 (default 800)"
},
"fullPage": {
"type": "boolean",
"description": "Capture the full scrollable page instead of just the viewport (costs 2 units instead of 1)"
},
"format": {
"type": "string",
"enum": [
"png",
"jpeg",
"webp"
],
"description": "Output image format (default png)"
}
}
}🟢render_pdf(url, html, width, height)
Render a public web page or an inline HTML snippet to a paginated PDF document, using a real headless browser (JS, CSS, and web fonts execute). Use this to turn a URL or HTML into a downloadable/printable PDF, e.g. an invoice, report, or saved article.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public http(s) URL to render (exactly one of url/html)"
},
"html": {
"type": "string",
"description": "Raw HTML to render (exactly one of url/html, max 1MB)"
},
"width": {
"type": "number",
"description": "Viewport width in pixels, 320-1920 (default 1280)"
},
"height": {
"type": "number",
"description": "Viewport height in pixels, 240-1080 (default 800)"
}
}
}🟢render_og(html, width, height)
Render an inline HTML snippet to a social-share (Open Graph) image sized for link previews, defaulting to the standard 1200x630 OG dimensions. Use this to generate og:image assets for blog posts, products, or share cards without hand-designing an image.
入力スキーマ
{
"type": "object",
"properties": {
"html": {
"type": "string",
"description": "Raw HTML to render into the OG image (required, max 100KB)"
},
"width": {
"type": "number",
"description": "Viewport width in pixels, 320-1920 (default 1200)"
},
"height": {
"type": "number",
"description": "Viewport height in pixels, 240-1080 (default 630)"
}
},
"required": [
"html"
]
}🟢extract_page(url, mode, schema)
Fetch a public web page and extract its content as either clean, readable markdown (the default) or as structured JSON fields matched against a caller-supplied schema. Use markdown mode to summarize or quote a page's text; use structured mode to pull specific named fields (e.g. price, title, author) out of a page's content.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public http(s) URL to extract (required)"
},
"mode": {
"type": "string",
"enum": [
"markdown",
"structured"
],
"description": "Extraction mode: 'markdown' (default, 2 units) returns cleaned page text as markdown; 'structured' (8 units, requires schema) returns JSON matched to the caller's field schema"
},
"schema": {
"type": "object",
"description": "Required when mode is 'structured': { properties: { field: { type: 'string'|'number'|'boolean'|'array' } } }, max 24 properties, max 8KB serialized"
}
},
"required": [
"url"
]
}コミュニティ
エビデンス