Skip to main content
Glama

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:

Pain Point

Manual Workflow

With AI Answer Copier

Extracting Q&A

10–15 min copying each line

2 seconds (auto-detect)

Formatting Math

20 min fixing broken symbols

Instant (KaTeX support)

LMS Upload

15 min manual CSV entry

1-click export

Total Prep Time

~45–60 minutes

< 1 minute

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


Related MCP server: MarkItDown MCP Server

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)

#

Tool

Output

Description

1

harmonize_markdown

.md

Standardize and normalize Markdown syntax (ATX headers, - list markers, fenced code blocks) without changing meaning

2

convert_to_txt

.txt

Strip all formatting to produce plain text

3

convert_to_html

.html

Full styled HTML document with GFM tables, KaTeX math, and embedded stylesheet

4

generate_html

HTML string

Generate self-contained HTML with all styles inlined (read-only, no file I/O)

5

convert_to_pdf

.pdf

Print-ready PDF via headless Chromium with full KaTeX math and syntax highlighting

6

convert_to_docx

.docx

Microsoft Word document with styled headings, lists, and code formatting

7

convert_to_latex

.tex

LaTeX source code with \section, list environments, and native math pass-through

8

convert_to_rtf

.rtf

Rich Text Format for legacy word processors and email clients

9

convert_to_csv

.csv

Extract GFM pipe-tables to comma-separated values

10

convert_to_json

.json

Structured JSON representation with sections, headings, lists, code blocks, and tables

11

convert_to_xml

.xml

Well-formed XML with <?xml?> declaration and structured elements

12

convert_to_xlsx

.xlsx

Excel spreadsheet — each Markdown table becomes a sheet

13

convert_to_image

.png

Full-page PNG screenshot via headless Chromium

14

convert_to_md

.md

Export Markdown to file, optionally harmonizing formatting first (harmonize=true)

15

convert_to_email_html

.html

Email-optimized HTML with all styles inlined, compatible with Outlook, Gmail, Apple Mail

Platform Converter Tools (10)

#

Tool

Target Platform

Description

16

convert_to_slack

Slack

mrkdwn format — bold as *, links as <url|text>, headers as bold text

17

convert_to_discord

Discord

Styled bold/underline headers, preserved code blocks

18

convert_to_jira

JIRA

Wiki markup — h1./h2., {code} blocks, [text|url] links

19

convert_to_confluence

Confluence

Wiki markup with {info}, {note} panels and {code:language=x} syntax

20

convert_to_asciidoc

AsciiDoc

= headers, ---- code blocks, url[text] links, image:: directives

21

convert_to_rst

reStructuredText

Underlined headers, .. code-block:: directives, RST reference syntax

22

convert_to_mediawiki

MediaWiki

== headers, '''bold''', <syntaxhighlight> tags, {\ wikitable

23

convert_to_bbcode

BBCode

[b], [i], [code], [url], [img] tags for phpBB/vBulletin forums

24

convert_to_textile

Textile

Markup for Redmine, Basecamp, and CMS platforms

25

convert_to_orgmode

Emacs Org Mode

* headers, #+BEGIN_SRC/#+END_SRC code, [[url][text]] links

Import Tools (1)

#

Tool

Description

26

html_to_markdown

Convert HTML content (full document or fragment) back to Markdown

Repair & Lint Tools (2)

#

Tool

Description

27

repair_markdown

Fix broken Markdown from LLM output or copy-paste — unclosed code fences, broken tables, stray emphasis markers, missing heading spaces, broken links

28

lint_markdown

Lint and report issues as JSON array with line number, severity, rule name, message, and fixable flag

Document Analysis Tools (5)

#

Tool

Description

29

extract_code_blocks

Extract all code blocks with language, content, and start/end line numbers

30

extract_links

Extract all links and images with text, URL, line number, and type (inline, reference, image, autolink)

31

generate_toc

Generate Markdown Table of Contents from headings with configurable max_depth (1–6)

32

analyze_document

Comprehensive statistics — line/word/character/paragraph/sentence counts, heading/code/table/link/image counts, estimated reading time

33

extract_structure

Bird's-eye document architecture — statistics, heading outline, code block summary, link summary

Batch Conversion (1)

#

Tool

Input

Description

34

batch_convert

items[] × formats[]

Batch-convert multiple Markdown documents to 22 formats in one call. Error-isolated per item+format. Optional output_dir for file output. Formats: txt, csv, json, xml, xlsx, latex, rtf, docx, pdf, html, md, email, slack, discord, jira, confluence, asciidoc, rst, mediawiki, bbcode, textile, orgmode


6 Built-in Prompts

Pre-configured prompt templates that orchestrate multiple tools:

Prompt

Description

convert-document

Convert Markdown to any supported format (PDF, DOCX, HTML, LaTeX, CSV, JSON, XML, XLSX, RTF, PNG, TXT, MD)

extract-tables

Extract all tables from Markdown and export as CSV or XLSX

format-for-sharing

Harmonize formatting, then convert to both PDF and HTML for distribution

analyze-and-repair

Lint → Repair → Re-lint to confirm all issues resolved

convert-for-platform

Convert Markdown to any platform format (Slack, Discord, JIRA, Confluence, AsciiDoc, RST, MediaWiki, BBCode, Textile, Org Mode)

document-overview

Full overview — statistics, TOC, code blocks, and links in one report


2 Resources

Resource URI

Description

markdown-formatter://supported-formats

Complete JSON list of all 23+ output formats with tool names and types

markdown-formatter://conversion-guide

Guide for choosing the right output format based on your use case


Quick Start

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:

#

Fix

Area

1

Browser not closed on error — try/finally around browser.close() so Chromium never leaks on PDF/PNG failures

Both transports

2

generate_html missing KaTeX CSS — restored viewport meta, KaTeX stylesheet (SRI hash), and full inline styles so math renders correctly

Vercel /api/mcp

3

convert_to_html incomplete styles — added SRI integrity hash, table borders, and blockquote styling to match local output

Vercel /api/mcp

4

Session map memory leak — instances Map now evicts stale sessions after 30 minutes (SESSION_TTL_MS); McpInstance tracks lastUsed

Vercel /api/mcp

5

keepAlive interval not cleared on normal SSE stream end — added inner try/finally that always calls clearInterval(keepAlive)

Vercel /api/mcp

6

_initialized SDK-internal access — replaced bare @ts-ignore with a typeof guard so the server fails gracefully after SDK upgrades

Vercel /api/mcp

7

No input size validation — added 1 GB hard limit (MAX_INPUT_BYTES) to all tool calls to prevent runaway CPU/memory on oversized payloads

Both transports

8

DELETE method creates new session — handler now returns 200 immediately on DELETE, preventing phantom session creation

Vercel /api/mcp


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 repository
git clone https://github.com/XJTLUmedia/AI_answer_copier.git

# Web app
npm install
npm run dev

# MCP server
cd mcp-server
npm install
npm run dev     # hot reload
npm run build   # production build
npm run inspector  # test with MCP Inspector

Tech Stack

Component

Technology

MCP SDK

@modelcontextprotocol/sdk

Markdown Parser

unified + remark + rehype

Math Rendering

remark-math + rehype-katex

Word Export

docx

Excel Export

xlsx

PDF/PNG Export

puppeteer

Schema Validation

zod

Runtime

Node.js (ESM)


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


Available Tools

33 tools
analyze_documentA
Read-onlyIdempotent

Analyze a Markdown document and return comprehensive statistics. Returns JSON with: line/word/character/paragraph/sentence counts, heading/code block/table/link/image/list/blockquote counts, and estimated reading time in minutes.

Inputs: markdown (required).

convert_to_asciidocA
Idempotent

Convert Markdown to AsciiDoc format. Transforms headers to = syntax, code blocks to ---- delimited blocks, links to url[text] syntax, and images to image::url[alt] directives.

Inputs: markdown (required), output_path.

convert_to_bbcodeA
Idempotent

Convert Markdown to BBCode format. Transforms formatting to [b], [i], [s], [code], [url], [img] tags. Used for forum posts on phpBB, vBulletin, and similar platforms.

Inputs: markdown (required), output_path.

convert_to_confluenceA
Idempotent

Convert Markdown to Confluence wiki markup. Similar to JIRA but includes Confluence-specific {info}, {note} panels and {code:language=x} syntax.

Inputs: markdown (required), output_path.

convert_to_csvA
Idempotent

Extract tables from Markdown and convert them to CSV format. Parses GFM pipe-tables from the input and outputs comma-separated values. If the Markdown contains multiple tables, they are concatenated with a blank line separator. Non-table content is ignored. If the Markdown contains no tables, returns an empty string. Side effects: when output_path is provided, writes the CSV to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns the CSV text directly as a string. Returns: CSV text string (if no output_path), or JSON { success, file_path, file_size_bytes, format } (if output_path set). Use this for lightweight tabular export or when downstream tools expect CSV. Prefer convert_to_xlsx for Excel-compatible spreadsheets with multiple sheets, or convert_to_json for structured data.

Inputs: markdown (required), output_path.

convert_to_discordA
Idempotent

Convert Markdown to Discord-compatible format. Transforms headers to styled bold/underline text that renders correctly in Discord messages. Code blocks and basic formatting are preserved.

Inputs: markdown (required), output_path.

convert_to_docxA
Idempotent

Convert Markdown to a Microsoft Word DOCX file. Produces a binary .docx document with styled headings, bold/italic text, numbered and bulleted lists, and code formatting. This is a binary format — output_path should almost always be provided. Side effects: when output_path is provided, writes the DOCX binary to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns a JSON object with { format: 'docx', file_size_bytes, hint, base64_preview } — the hint will tell you to re-call with output_path to save the file. Returns: JSON write-confirmation (if output_path set), or JSON binary-guidance object (if omitted). Use this for Word-compatible documents. Prefer convert_to_rtf for legacy word processors, convert_to_pdf for read-only distribution, or convert_to_html for web.

Inputs: markdown (required), output_path.

convert_to_email_htmlA
Idempotent

Convert Markdown to email-optimized HTML with all styles inlined. Produces HTML compatible with Outlook, Gmail, Apple Mail, and other email clients. No external CSS dependencies. Wraps content in a responsive email table layout.

Inputs: markdown (required), output_path.

convert_to_htmlA
Idempotent

Convert Markdown to a complete, styled HTML document. Renders GFM (tables, task lists, strikethrough) and KaTeX math into semantic HTML with an embedded stylesheet for clean presentation. The output is a full document with (charset, KaTeX CSS CDN link, inline styles) and . Side effects: when output_path is provided, writes the HTML file to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns the full HTML string directly. Returns: HTML document string (if no output_path), or JSON { success, file_path, file_size_bytes, format } (if output_path set). Use this when you need a file saved to disk or when you need the full document. Prefer generate_html if you only need the HTML string returned directly (no file I/O) and want inline styles without a CDN link. Prefer convert_to_pdf for print-ready output, or convert_to_image for a visual snapshot.

Inputs: markdown (required), output_path.

convert_to_imageA
Idempotent

Convert Markdown to a PNG image. Renders the Markdown as styled HTML (GFM tables, KaTeX math) and takes a full-page screenshot via a headless Chromium browser (Puppeteer). Requires a locally installed Chrome, Edge, or Chromium — set PUPPETEER_EXECUTABLE_PATH env var to override auto-detection. This is a binary format — output_path should almost always be provided. Side effects: launches a transient headless browser process (no persistent state; may fetch KaTeX CDN stylesheet). When output_path is provided, writes the PNG to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns JSON { format: 'png', file_size_bytes, hint, base64_preview }. Returns: JSON write-confirmation (if output_path set), or JSON binary-guidance object (if omitted). Use this when you need a visual snapshot of the rendered Markdown (e.g. for embedding in chat, previews, social cards). Prefer convert_to_pdf for paginated print output, or convert_to_html for interactive web content.

Inputs: markdown (required), output_path.

convert_to_jiraA
Idempotent

Convert Markdown to JIRA wiki markup. Transforms headers to h1./h2., bold to single asterisks, code blocks to {code} blocks, links to [text|url], and lists to JIRA * and # syntax.

Inputs: markdown (required), output_path.

convert_to_jsonA
Idempotent

Convert Markdown to a structured JSON representation. Parses the document into a JSON object with the document title as the root key, containing arrays of section objects with headings, paragraphs, lists, code blocks, and tables. Useful for programmatic analysis or feeding structured content into other systems. Side effects: when output_path is provided, writes the JSON to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns the JSON string directly. Returns: JSON string (if no output_path), or JSON { success, file_path, file_size_bytes, format } (if output_path set). Use this when you need a machine-readable AST-like representation of the Markdown content. Prefer convert_to_xml for XML-based interchange, or convert_to_csv/convert_to_xlsx for tabular data extraction.

Inputs: markdown (required), title, output_path.

convert_to_latexA
Idempotent

Convert Markdown to LaTeX source code. Produces a LaTeX document fragment with \section, \textbf, \textit, \begin{itemize}/\begin{enumerate} list environments, verbatim code blocks, and table environments. KaTeX math expressions in the Markdown are passed through as native LaTeX math. Side effects: when output_path is provided, writes the .tex file to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns the LaTeX source as a string. Returns: LaTeX source string (if no output_path), or JSON { success, file_path, file_size_bytes, format } (if output_path set). Use this when you need to embed content in a LaTeX workflow or compile to PDF via pdflatex/xelatex externally. For direct PDF output without a LaTeX toolchain, use convert_to_pdf instead.

Inputs: markdown (required), output_path.

convert_to_mdA
Idempotent

Export Markdown content, optionally harmonizing its formatting first. When harmonize=false (default), returns the input Markdown unchanged. When harmonize=true, applies the same normalization as harmonize_markdown (ATX-style headers, '-' list markers, fenced code blocks, consistent indentation) before returning. Side effects: when output_path is provided, writes the Markdown to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns the Markdown string directly. Returns: Markdown string (if no output_path), or JSON { success, file_path, file_size_bytes, format } (if output_path set). Use this when you want to save Markdown to a file (with or without cleanup). Prefer harmonize_markdown if you only want to normalize formatting without saving to disk. Use the convert_to_* family for other output formats.

Inputs: markdown (required), harmonize, output_path.

convert_to_mediawikiA
Idempotent

Convert Markdown to MediaWiki markup. Transforms headers to == syntax, bold to triple quotes, code to tags, and tables to {| wikitable format.

Inputs: markdown (required), output_path.

convert_to_orgmodeA
Idempotent

Convert Markdown to Emacs Org Mode format. Transforms headers to * syntax, bold to text, code blocks to #+BEGIN_SRC/#+END_SRC, and links to [[url][text]] syntax.

Inputs: markdown (required), output_path.

convert_to_pdfA
Idempotent

Convert Markdown to a PDF document. Renders the Markdown as styled HTML (GFM tables, KaTeX math) and then prints it to PDF via a headless Chromium browser (Puppeteer). Requires a locally installed Chrome, Edge, or Chromium — set PUPPETEER_EXECUTABLE_PATH env var to override auto-detection. This is a binary format — output_path should almost always be provided. Side effects: launches a transient headless browser process for rendering (no network requests are made for the conversion itself, though the HTML references a CDN KaTeX stylesheet which may be fetched). When output_path is provided, writes the PDF to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns JSON { format: 'pdf', file_size_bytes, hint, base64_preview }. Returns: JSON write-confirmation (if output_path set), or JSON binary-guidance object (if omitted). Use this for high-fidelity, print-ready document output. Prefer convert_to_html for web-viewable output, convert_to_docx for editable documents, or convert_to_latex for LaTeX toolchains.

Inputs: markdown (required), output_path.

convert_to_rstA
Idempotent

Convert Markdown to reStructuredText (RST) format. Transforms headers to underlined text, code blocks to .. code-block:: directives, and links to RST reference syntax.

Inputs: markdown (required), output_path.

convert_to_rtfA
Idempotent

Convert Markdown to Rich Text Format (RTF). Produces an RTF document string preserving basic formatting: bold, italic, headers (as styled paragraphs), lists, and code blocks. Side effects: when output_path is provided, writes the RTF file to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns the raw RTF markup as a string. Returns: RTF markup string (if no output_path), or JSON { success, file_path, file_size_bytes, format } (if output_path set). Use this when the target application requires RTF (e.g. legacy word processors, email clients). Prefer convert_to_docx for modern Word documents, or convert_to_html for web display.

Inputs: markdown (required), output_path.

convert_to_slackA
Idempotent

Convert Markdown to Slack mrkdwn format. Transforms bold (**) to single asterisks, italic to underscores, links to Slack <url|text> syntax, and headers to bold text. Use this when pasting formatted content into Slack messages.

Inputs: markdown (required), output_path.

convert_to_textileA
Idempotent

Convert Markdown to Textile markup format. Used by Redmine, older versions of Basecamp, and some CMS platforms.

Inputs: markdown (required), output_path.

convert_to_txtA
Idempotent

Convert Markdown to plain text by stripping all formatting — removes headers, bold/italic markers, links, images, code fences, and HTML tags. The result is a human-readable plain-text string with no markup. This is a destructive conversion: formatting information is permanently lost. Side effects: when output_path is provided, writes the plain text to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns the plain text string directly. Returns: plain text string (if no output_path), or JSON { success, file_path, file_size_bytes, format } (if output_path set). Use this instead of convert_to_md when you need formatting-free content (e.g. for indexing, search, or clipboard). Use convert_to_html or convert_to_pdf if you need to preserve the document's visual structure.

Inputs: markdown (required), output_path.

convert_to_xlsxA
Idempotent

Convert Markdown tables to a Microsoft Excel XLSX spreadsheet. Parses GFM pipe-tables from the input and creates an Excel workbook. Each table becomes a sheet in the workbook. Non-table content is ignored. If the Markdown contains no tables, produces an empty workbook. This is a binary format — output_path should almost always be provided. Side effects: when output_path is provided, writes the XLSX binary to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns JSON { format: 'xlsx', file_size_bytes, hint, base64_preview }. Returns: JSON write-confirmation (if output_path set), or JSON binary-guidance object (if omitted). Use this when you need a full Excel file with formatting. Prefer convert_to_csv for lightweight plain-text tabular export, or convert_to_json for structured programmatic access.

Inputs: markdown (required), output_path.

convert_to_xmlA
Idempotent

Convert Markdown to an XML document. Parses the Markdown into a structured XML tree with a root element named after the title parameter, containing , , , , , and elements. Produces well-formed XML with an declaration. Side effects: when output_path is provided, writes the XML to disk (creates parent directories, overwrites existing files). When output_path is omitted, returns the XML string directly. Returns: XML string (if no output_path), or JSON { success, file_path, file_size_bytes, format } (if output_path set). Use this for XML-based data interchange or when downstream systems require XML input. Prefer convert_to_json for JSON APIs, convert_to_html for XHTML/web content, or convert_to_csv for flat tabular data.

Inputs: markdown (required), title, output_path.

extract_code_blocksA
Read-onlyIdempotent

Extract all code blocks from a Markdown document. Returns a JSON array of code blocks, each with language, code content, and start/end line numbers. Useful for extracting code snippets from LLM responses or documentation.

Inputs: markdown (required).

extract_structureA
Read-onlyIdempotent

Extract the full structure of a Markdown document. Returns JSON with document statistics, heading outline, code block summary (language, line count, positions), and link summary (totals by type, unique URL count). Provides a bird's-eye view of document architecture.

Inputs: markdown (required).

generate_htmlA
Read-onlyIdempotent

Generate a complete, self-contained HTML document from Markdown with all styles inlined. Renders GFM (tables, task lists, strikethrough) and KaTeX math into a full HTML page with an embedded block and a KaTeX CSS CDN link. Returns the HTML string directly — no file is written to disk. Side effects: none. This tool is read-only and performs no file I/O. Returns: a complete HTML document string (…) with inline styles, ready for rendering in a browser. The optional title parameter sets the tag in the HTML section. Use this when you need styled HTML output returned as a string (e.g., for embedding in responses or previewing). Prefer convert_to_html when you need to write the HTML to a file on disk. Prefer convert_to_pdf or convert_to_image for non-HTML visual output formats.

Inputs: markdown (required), title.

generate_tocA
Read-onlyIdempotent

Generate a Table of Contents from Markdown headings. Returns a Markdown-formatted TOC with indented links to each heading. Handles duplicate heading slugs. The max_depth parameter controls the deepest heading level to include.

Inputs: markdown (required), max_depth.

harmonize_markdownA
Idempotent

Standardize and normalize Markdown syntax without changing the document's meaning. Re-formats headers (ATX-style), normalizes list markers to '-', enforces fenced code blocks with backticks, and applies consistent indentation. Side effects: when output_path is provided, writes the harmonized Markdown to disk (creates parent directories as needed, overwrites existing files). When output_path is omitted, returns the harmonized text as a string with no file I/O. Returns: harmonized Markdown string (if no output_path), or JSON with { success, file_path, file_size_bytes, format } (if output_path set). Use this tool when you need to clean up inconsistent Markdown formatting before further processing. Prefer convert_to_md with harmonize=true if you also need to save the result, as it combines both steps. Not suitable for converting Markdown to other formats — use the convert_to_* tools instead.

Inputs: markdown (required), output_path.

html_to_markdownA
Idempotent

Convert HTML to Markdown. Performs round-trip import of HTML content back to Markdown format. Handles headings, tables, lists, code blocks, links, images, and inline formatting. Useful for importing web content or converting HTML emails to Markdown.

Inputs: html (required), output_path.

lint_markdownA
Read-onlyIdempotent

Lint Markdown and report issues. Returns a JSON array of lint issues found in the document, each with line number, column, severity (error/warning/info), rule name, message, and fixable flag. Checks for: missing heading spaces, trailing whitespace, inconsistent list markers, hard tabs, multiple blank lines, bare URLs, unclosed emphasis, and unclosed code fences.

Inputs: markdown (required).

repair_markdownA
Idempotent

Repair broken Markdown from LLM output or copy-paste. Fixes unclosed code fences, broken tables (mismatched columns, missing separators), stray emphasis markers, missing heading spaces, inconsistent list indentation, broken links, and excessive whitespace.

Inputs: markdown (required), output_path.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 33 tools

    Disambiguation3/5

    Significant overlap exists between convert_to_html and generate_html (both produce HTML, differing only in file I/O behavior) and between convert_to_md with harmonize=true and harmonize_markdown (identical functionality). These duplications force agents to carefully read descriptions to distinguish tools that could have been parameters or a single tool.

    Naming Consistency4/5

    The vast majority of tools follow a strict verb_noun convention (convert_to_*, extract_*, generate_*, harmonize_*, lint_*, repair_*). However, html_to_markdown breaks this pattern (should be convert_from_html or import_html), and analyze_document is slightly vague compared to the specific extract_* tools.

    Tool Count2/5

    With 33 tools, this significantly exceeds the 25+ threshold where count becomes overwhelming. The server converts Markdown to 20+ formats, but this could be consolidated into a single convert tool with a format parameter, reducing surface area and cognitive load for agents.

    Completeness4/5

    Excellent coverage of Markdown export formats (20+ targets), analysis (lint, statistics, structure extraction), and repair operations. Minor gap: only supports HTML as an input format (html_to_markdown), lacking import from Word, PDF, or other common formats for a fully bidirectional converter.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that converts various file formats (PDF, PowerPoint, Word, Excel, Images, etc.) to Markdown to make them accessible to LLMs.
      1
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      A Model Context Protocol server that converts over 29 file formats, including PDFs, Office documents, and audio, into structured Markdown using Microsoft's MarkItDown library. It enables AI assistants to process diverse document types through single file conversion and batch directory processing.
      3
      149 PyPI
      49
      MIT
    • A
      license
      A
      quality
      Not graded
      maintenance
      An MCP server that enables AI agents to instantly convert Markdown into beautiful, ready-to-deliver Word, PDF, HTML with sidebars, and Slideshow documents, bridging the "last mile" of AI content generation.
      7
      28 npm
      1
      -