PDFSpark MCP
Convert agent-authored HTML or live URLs into PDF documents using a Playwright-powered MCP server for specs, handoffs, and customer-facing exports.
Overview
PDFSpark MCP is a MCP server for the Build phase that converts HTML or URLs to PDF documents powered by Playwright for agent-driven documentation exports.
What is this MCP server?
- Converts HTML strings or URLs to PDF via Playwright rendering
- stdio MCP via npx pdfspark-mcp (npm 1.2.0)
- GitHub backing repo softvoyagers/pdfspark-api
- Fits agent workflows that already produce HTML READMEs or report pages
- Useful for invoices, proposals, and exported help content without a separate print CSS pipeline
- Server version 1.2.0 (MCP 2025-12-11 schema)
- Playwright-powered conversion per catalog description
- npm package pdfspark-mcp, stdio transport
What problem does it solve?
You have HTML or a live page but stakeholders want a PDF and manual print-to-PDF wastes time and drifts from the agent workflow.
Who is it for?
Solo builders exporting specs, guides, or one-off reports from agent-generated HTML or staging URLs.
Skip if: High-volume transactional PDF mail merge, legally templated e-sign PDFs, or complex paginated publishing suites.
What do I get? / Deliverables
Your agent generates PDFs from the same HTML or URLs you already use, giving you shareable docs without a separate rendering setup.
- PDF files generated from supplied HTML or URLs
- Repeatable agent-driven export for docs and handoffs
- Playwright-rendered layouts consistent with web view
Recommended MCP Servers
Journey fit
PDFs are a common deliverable while building products—quotes, one-pagers, technical docs, and printable reports—often before formal launch tooling exists. Docs subphase is the primary shelf because URL/HTML-to-PDF is how solo builders freeze web content into shareable documentation artifacts.
How it compares
MCP HTML-to-PDF renderer, not a screenshot-only or static hosting server.
Common Questions / FAQ
Who is PDFSpark MCP for?
Developers using MCP agents who need Playwright-based PDF generation from HTML or URLs during build and documentation work.
When should I use PDFSpark MCP?
Use it when you must deliver a PDF version of a web page, report HTML, or documentation URL before or alongside ship.
How do I add PDFSpark MCP to my agent?
Register stdio MCP with npx pdfspark-mcp (version 1.2.0) in your client config, then pass HTML or a URL to the conversion tools.