Markdown Formatter

AI Answer Copier — MCP-Powered Multi-Format Exporter

Turn "AI Noise" into "Classroom Ready" in 5 Seconds.

[npm version] [License: MIT] [MCP Registry] [Glama] [GitHub]

A Model Context Protocol (MCP) server that gives your AI assistant the power to convert Markdown into 22 professional document formats, batch-convert multiple documents across 22 formats in one call, analyze documents, repair broken Markdown, and convert across platforms — all without leaving your AI chat.

npm: https://www.npmjs.com/package/@xjtlumedia/markdown-mcp-server

Why This Exists

You asked an AI to write 20 questions. It delivered. But now you're stuck:

Generating content takes seconds. Formatting it for the real world takes an hour. This MCP server eliminates that gap entirely.

Live Demo

Online web version (no install needed): ai-answer-copier.vercel.app

Test MCP tool in inspector:

Use actual MCP instance:

All 34 MCP Tools

Document Conversion Tools (15)

Platform Converter Tools (10)

Import Tools (1)

Repair & Lint Tools (2)

Document Analysis Tools (5)

Batch Conversion (1)

6 Built-in Prompts

Pre-configured prompt templates that orchestrate multiple tools:

2 Resources

Quick Start

Install via npx (Recommended)

No installation needed — just configure your MCP client:

{  "mcpServers": {    "ai-answer-copier": {      "command": "npx",      "args": ["-y", "@xjtlumedia/markdown-mcp-server"]    }  }}

Install Globally

npm install -g @xjtlumedia/markdown-mcp-server

Then configure:

{  "mcpServers": {    "ai-answer-copier": {      "command": "markdown-mcp-server"    }  }}

Configuration by AI Client

🔌 Claude Desktop

Edit %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{  "mcpServers": {    "ai-answer-copier": {      "command": "npx",      "args": ["-y", "@xjtlumedia/markdown-mcp-server"]    }  }}

Restart Claude Desktop. You'll see a 🔌 icon — all 34 tools are now available.

VS Code (GitHub Copilot)

Add to .vscode/mcp.json or VS Code settings:

{  "servers": {    "ai-answer-copier": {      "command": "npx",      "args": ["-y", "@xjtlumedia/markdown-mcp-server"]    }  }}

Cursor / Windsurf / Any MCP Client

Use the same npx command pattern above in your client's MCP configuration.

DIY version (local build)

{  "mcpServers": {    "markdown-formatter": {      "command": "node",      "args": [        "YOUR_PATH_TO_PROJECT/mcp-server/dist/mcp-server/src/index.js"      ]    }  }}

Replace YOUR_PATH_TO_PROJECT with the absolute path to this folder.

HTTP Mode (Vercel)

A hosted HTTP endpoint is available for browser-based and remote integrations:

https://ai-answer-copier.vercel.app/api/mcp

Test with MCP Inspector:

npx @modelcontextprotocol/inspector https://ai-answer-copier.vercel.app/api/mcp

Usage Examples

Once connected, just talk to your AI naturally:

"Batch-convert 5 markdown documents into DOCX, PDF, and HTML simultaneously and save them to my Downloads folder." → AI uses batch_convert with items[] and formats[]

"Generate 10 physics questions about Newton's Laws and export them as a Kahoot CSV." → AI uses convert_to_csv

"Convert this markdown into a Word document and save it to my Desktop." → AI calls convert_to_docx with output_path

"Take these lecture notes and produce a print-ready PDF." → AI calls convert_to_pdf with Puppeteer rendering, KaTeX math, and syntax highlighting

"Turn this into a Moodle-compatible XML quiz bank." → AI calls convert_to_xml

"Format this for Slack and send it to the team channel." → AI calls convert_to_slack

"Check this Markdown for issues and fix them." → AI calls lint_markdown then repair_markdown

"Give me an overview of this document — word count, structure, all links." → AI chains analyze_document + generate_toc + extract_links

Features

22 Output Formats

Export to PDF, DOCX, HTML, LaTeX, CSV, JSON, XML, XLSX, RTF, PNG, TXT, Markdown — plus Slack, Discord, JIRA, Confluence, AsciiDoc, RST, MediaWiki, BBCode, Textile, Org Mode, and Email HTML.

Batch Conversion

Convert multiple Markdown documents to multiple formats in one batch_convert call. Errors are isolated per item+format so one failure never blocks the rest.

Math & Code as First-Class Citizens

Full support for KaTeX math expressions and syntax-highlighted code blocks. Your $\sqrt{x^2 + y^2}$ and Python snippets survive every conversion perfectly.

Smart Binary Handling

Binary formats (PDF, DOCX, XLSX, PNG) don't dump raw base64 into chat. The server returns actionable guidance so the AI knows to save to a file path.

Document Analysis & Repair

Lint Markdown, auto-repair broken formatting, extract code blocks and links, generate Table of Contents, and get comprehensive document statistics — all without leaving the chat.

GFM (GitHub Flavored Markdown)

Tables, task lists, strikethrough, autolinks — all parsed correctly via remark-gfm.

Puppeteer-Powered PDF & PNG

PDF and image exports use headless Chromium for pixel-perfect rendering with full CSS styling, KaTeX math, syntax highlighting, and print-optimized layouts.

Self-Contained

Zero runtime dependencies on external APIs. Everything runs locally. Your data never leaves your computer.

Architecture

┌─────────────────────────┐│  AI Client               ││  (Claude, Copilot,      ││   Cursor, Windsurf)     │└──────────┬──────────────┘           │ MCP Protocol (stdio / HTTP)           ▼┌─────────────────────────┐│  AI Answer Copier        ││  MCP Server (34 tools)   ││                          ││  ┌── Conversion ────────┐││  │ remark/rehype, docx, │││  │ puppeteer, xlsx,     │││  │ CSV/JSON/XML/RTF/    │││  │ LaTeX/TXT parsers    │││  └──────────────────────┘││  ┌── Platform ──────────┐││  │ Slack, Discord, JIRA,│││  │ Confluence, AsciiDoc,│││  │ RST, MediaWiki,      │││  │ BBCode, Textile, Org │││  └──────────────────────┘││  ┌── Batch ─────────────┐││  │ items[] × formats[]  │││  │ 22 formats, isolated │││  └──────────────────────┘││  ┌── Analysis ──────────┐││  │ Code blocks, links,  │││  │ TOC, stats, structure│││  └──────────────────────┘││  ┌── Repair ────────────┐││  │ Lint, auto-repair    │││  └──────────────────────┘││  ┌── Import ────────────┐││  │ HTML → Markdown      │││  └──────────────────────┘│└─────────────────────────┘

What's New in v2.1.0

This release hardens both the local (npx) and remote Vercel MCP transports with 8 logic fixes:

Known Limitations

• PDF / PNG require local Chromium — convert_to_pdf and convert_to_image launch a headless browser. This works fine with npx but is unavailable on Vercel's free tier (no bundled Chromium). Set the PUPPETEER_EXECUTABLE_PATH environment variable to point to your local Chrome if auto-detection fails.
• Chromium version on Vercel — the remote endpoint uses @sparticuz/chromium-min with a pinned tar at v131.0.1. If Vercel bumps the Lambda runtime you may need to update the CHROMIUM_TAR_URL env var.
• 1 MB input limit — all tool calls reject inputs larger than 1 MB. Split large documents into sections before converting.
• Session TTL (remote only) — sessions on the Vercel endpoint expire after 30 minutes of inactivity. Long-running stateful workflows should issue periodic keep-alive calls.

Development

# Clone the repositorygit clone https://github.com/XJTLUmedia/AI_answer_copier.git
# Web appnpm installnpm run dev
# MCP servercd mcp-servernpm installnpm run dev     # hot reloadnpm run build   # production buildnpm run inspector  # test with MCP Inspector

Tech Stack

Contributing

We welcome contributions! Whether it's a new export format, a bug fix, or documentation improvement — please consider making a pull request.

1. Fork the repository
2. Create a feature branch
3. Submit a pull request

License

MIT © XJTLUmedia

Built by educators, for educators.
Reclaim 5 hours of your week. Let the AI handle the formatting.