{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreih44ld5ntrauhe7o7cffy5xsq6vq3sekg2wpu3talmppzmvrhwnie",
    "uri": "at://did:plc:25rdn5elo5izoxrmtis34zuk/app.bsky.feed.post/3mpubjifgkdv2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreidkd6bphybntfs6eio7l6pua4ghgtqnqwkzxlw7nkv6v642gj6rxm"
    },
    "mimeType": "image/webp",
    "size": 49684
  },
  "path": "/paperquire_e3fdb510bbe49c/paperquire-v030-your-ai-agents-pdf-tool-3c1n",
  "publishedAt": "2026-07-04T23:23:10.000Z",
  "site": "https://dev.to",
  "tags": [
    "release",
    "mcp",
    "ai",
    "Model Context Protocol",
    "Upgrade to Pro",
    "Download v0.3.0",
    "MCP setup guide",
    "CLI Reference"
  ],
  "textContent": "##  AI agents can now generate PDFs\n\nLarge language models are great at producing Markdown. What they can't do is turn that Markdown into a polished, branded PDF. That's always been a manual step — copy the output, paste it somewhere, fiddle with formatting, export.\n\nPaperQuire v0.3.0 removes that step entirely. The app now includes a built-in Model Context Protocol (MCP) server. Any MCP-compatible AI agent — Claude, ChatGPT, Copilot, or others — can call PaperQuire directly as a tool to render Markdown into professional documents.\n\n##  What is MCP?\n\nMCP is an open protocol that lets AI applications call external tools over a standard JSON-RPC interface. Think of it as \"USB-C for AI tools\" — one protocol, many tools. When you configure PaperQuire as an MCP server, your AI agent discovers its capabilities automatically and can call them during a conversation.\n\n##  How it works\n\nRun the MCP server as a CLI subcommand:\n\n\n\n    paperquire mcp-server\n\n\nThe server exposes four tools:\n\n  * **render** — convert Markdown to PDF with full template and branding support\n  * **list_templates** — discover all 8 built-in templates\n  * **show_template** — inspect a template's design tokens, cover style, and page config\n  * **batch_render** — render multiple documents in one call (Pro)\n\n\n\nIt also exposes a `paperquire://config` resource that returns your project's `.paperquire.yml` configuration, so the agent can discover your preferred template and branding before rendering.\n\n##  Setup\n\n###  Claude Desktop\n\nAdd this to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):\n\n\n\n    {\n      \"mcpServers\": {\n        \"paperquire\": {\n          \"command\": \"paperquire\",\n          \"args\": [\"mcp-server\"]\n        }\n      }\n    }\n\n\nRestart Claude Desktop, and you'll see PaperQuire's tools in the MCP panel.\n\n###  Claude Code\n\nAdd to your project's `.mcp.json`:\n\n\n\n    {\n      \"mcpServers\": {\n        \"paperquire\": {\n          \"command\": \"paperquire\",\n          \"args\": [\"mcp-server\"]\n        }\n      }\n    }\n\n\n###  VS Code (GitHub Copilot)\n\nAdd to `.vscode/mcp.json`:\n\n\n\n    {\n      \"mcp\": {\n        \"servers\": {\n          \"paperquire\": {\n            \"command\": \"paperquire\",\n            \"args\": [\"mcp-server\"]\n          }\n        }\n      }\n    }\n\n\n##  What you can ask your agent to do\n\nOnce configured, you can ask things like:\n\n> \"Write a project status report for Q2 and render it as a branded PDF.\"\n>\n> \"What templates does PaperQuire have? Show me the technical design template, then use it to render my spec.\"\n>\n> \"Render all the markdown files in my docs/ folder as PDFs with the corporate template.\"\n\nThe agent generates the content, calls PaperQuire's MCP tools, and reports back with the file path. No manual steps.\n\n##  Architecture\n\nThe MCP server reuses PaperQuire's existing Electron-based render pipeline — the same Chromium engine behind the desktop app's live preview and PDF export. This means MCP-rendered PDFs are identical to what you'd get from the GUI or CLI.\n\nA few design decisions worth noting:\n\n  * **Long-running renderer** — unlike the CLI (which creates and destroys a renderer per command), the MCP server keeps one alive and reuses it across all tool calls. First render takes a few seconds; subsequent ones are fast.\n  * **Stdout isolation** — MCP uses stdout exclusively for JSON-RPC. PaperQuire suppresses Chromium's startup noise on stdout so it doesn't interfere with the protocol.\n  * **Render lock** — the Chromium renderer is single-threaded, so concurrent tool calls are serialized with a Promise-based mutex.\n\n\n\n##  Free tier\n\nThe same daily limits apply: 3 free renders per day. Upgrade to Pro for unlimited renders and batch export.\n\n##  Get it\n\n  * Download v0.3.0 for macOS, Windows, or Linux\n  * MCP setup guide for full configuration and tool reference\n  * CLI Reference for all commands including `mcp-server`\n\n\n\nOr install via Homebrew:\n\n\n\n    brew install --cask paperquire/paperquire/paperquire\n",
  "title": "PaperQuire v0.3.0 — Your AI Agent's PDF Tool"
}