spa-reader-mcp
This server renders JavaScript Single Page Applications (SPAs) using a headless Chromium browser, enabling content extraction and screenshot capture.
Extract SPA content as Markdown: Render JavaScript-heavy pages and extract clean, LLM-ready Markdown with optional YAML frontmatter (title, author, excerpt).
Capture screenshots: Take PNG screenshots of rendered pages with configurable viewport dimensions (320–3840px width, 240–2160px height) and full-page capture support.
Wait for dynamic content: Specify CSS selectors to wait for before extraction or screenshot, ensuring content is fully rendered.
Authentication & custom requests: Inject cookies and custom HTTP headers to access protected or API-gated content.
Configure timeouts: Set navigation timeouts (1–120 seconds) to control rendering wait time.
Security: Built-in SSRF protection (blocks private/loopback IPs), HTTP/HTTPS-only scheme restriction, selector injection prevention, and 100KB content size cap.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@spa-reader-mcpextract the article content from https://react.dev/blog"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
spa-reader-mcp
MCP server that renders JavaScript SPA pages and extracts Markdown via headless Chromium.
Traditional scrapers fail on SPAs because content is rendered client-side. This tool launches Playwright, waits for JS to finish, then extracts clean Markdown using Readability + Turndown.
Install
npx playwright install chromiumClaude Desktop
{
"mcpServers": {
"spa-reader": {
"command": "npx",
"args": ["-y", "spa-reader-mcp"]
}
}
}Claude Code
claude mcp add spa-reader -- npx -y spa-reader-mcpTools
spa_read
Render a page and extract content as Markdown.
Parameter | Type | Default | Description |
| string | — | URL to read (required) |
| string | — | CSS selector to wait for |
| number | 30000 | Timeout in ms |
| boolean | true | Add YAML frontmatter |
| array | — | Cookies for auth |
| object | — | Custom HTTP headers |
spa_screenshot
Capture a PNG screenshot after JS rendering.
Parameter | Type | Default | Description |
| string | — | URL to capture (required) |
| string | — | CSS selector to wait for |
| number | 30000 | Timeout in ms |
| number | 1280 | Viewport width |
| number | 720 | Viewport height |
| boolean | false | Full page capture |
| array | — | Cookies for auth |
| object | — | Custom HTTP headers |
Security
SSRF protection: blocks private/loopback IPs
Only
http:andhttps:schemes allowedSelector injection prevention
Content capped at 100KB
Dev
pnpm install && pnpm build
pnpm testLicense
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/XXO47OXX/spa-reader-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server