Generate Branded PDFs Directly from Claude Code with PaperQuire v0.3.0's

Key Takeaways

• PaperQuire v0.3.0's MCP server lets Claude Code render Markdown to branded PDFs.
• Add paperquire mcp-server to .mcp.json and ask for a PDF.

What Changed — PaperQuire v0.3.0 Adds an MCP Server for PDF Generation

PaperQuire v0.3.0, released recently, introduces a built-in Model Context Protocol (MCP) server. This means any MCP-compatible AI agent — including Claude Code — can now generate polished, branded PDFs from Markdown without leaving your terminal.

Previously, if you wanted Claude Code to produce a PDF, you'd get Markdown output and then manually copy it into a tool like Pandoc or a word processor. That workflow is gone. PaperQuire's MCP server exposes four tools that Claude Code can call directly:

• render — Convert Markdown to PDF with full template and branding support
• list_templates — Discover all 8 built-in templates
• show_template — Inspect a template's design tokens, cover style, and page config
• batch_render — Render multiple documents in one call (Pro feature)

The server also exposes a paperquire://config resource that returns your project's .paperquire.yml configuration, so Claude Code can discover your preferred template and branding before rendering.

What It Means For You — No More Manual PDF Export

If you generate reports, specs, or documentation with Claude Code, this MCP server eliminates the final manual step. You can now ask Claude Code to:

• "Write a project status report for Q2 and render it as a branded PDF."
• "What templates does PaperQuire have? Show me the technical design template, then use it to render my spec."
• "Render all the markdown files in my docs/ folder as PDFs with the corporate template."

Claude Code generates the content, calls PaperQuire's MCP tools, and reports back with the file path. No copy-paste, no formatting fiddling.

Under the hood, PaperQuire reuses its Electron-based Chromium render pipeline, so MCP-rendered PDFs are identical to what you'd get from the GUI or CLI. The MCP server keeps a long-running renderer alive — the first render takes a few seconds, but subsequent ones are fast.

Try It Now — Setup in Your Claude Code Project

1. Install PaperQuire (if you haven't already):

   brew install --cask paperquire/paperquire/paperquire
   

   Or download v0.3.0 from the releases page.

2. Add the MCP server to your project's .mcp.json:

   {
     "mcpServers": {
       "paperquire": {
         "command": "paperquire",
         "args": ["mcp-server"]
       }
     }
   }
   

3. Restart Claude Code and verify the tools appear in the MCP panel.

4. Ask Claude Code to render something:

   Claude, write a brief project update and render it as a PDF using PaperQuire's default template.
   

Important: PaperQuire's free tier allows 3 renders per day. Upgrade to Pro for unlimited renders and batch export.

Architecture Notes for Power Users

• Stdout isolation: PaperQuire suppresses Chromium's startup noise on stdout so it doesn't interfere with the JSON-RPC protocol.
• Render lock: The Chromium renderer is single-threaded, so concurrent tool calls are serialized with a Promise-based mutex. This shouldn't affect most workflows, but be aware if you're batching many renders.

For full configuration and tool reference, see the MCP setup guide.

Source: dev.to

[Updated 07 Jul via devto_claudecode]

Separately, a Hacker News user reports that Claude Code's default data retention policy is only 30 days, warning of potential transcript loss unless users manually update cleanupPeriodDays in settings.json [per HN]. This operational detail, confirmed in an Anthropic GitHub issue, is relevant for PaperQuire users who rely on Claude Code's session history for PDF generation workflows.

[Updated 08 Jul via devto_claudecode]

Separately, new reports reveal Anthropic's Claude Code contained a hidden tracker that secretly monitored Chinese users, prompting Alibaba to ban the tool internally and direct employees to switch to Qoder [per Tom's Hardware]. Anthropic has described the tracker as an "experiment" [per Malwarebytes]. This development adds a layer of geopolitical risk for agencies using Claude Code in cross-border workflows.