inktomd MCP Server

Convert any ArXiv research paper to clean structured Markdown. Accepts both abstract page URLs (arxiv.org/abs/PAPER_ID) and direct PDF links (arxiv.org/pdf/PAPER_ID). Returns the full paper content with headings, sections, and content preserved — uses significantly fewer tokens than the PDF format for AI analysis.

Convert multiple URLs to Markdown in a single call. Maximum 10 URLs per batch. Each URL is converted independently. Args: urls: List of URLs to convert. Maximum 10. Each must start with http:// or https:// Returns: All converted Markdown documents combined, clearly separated with headers

Convert a local file to clean AI-ready Markdown. Supports PDF, Word (.doc/.docx), Excel (.xls/.xlsx), PowerPoint (.ppt/.pptx), EPUB, HTML, CSV, JSON, XML, Jupyter notebooks (.ipynb), Email files (.eml/.msg), ZIP archives (.zip), and 7-Zip archives (.7z). Provide the absolute file path. Maximum file size: 20MB.

Convert any URL to clean AI-ready Markdown. Supports webpages, YouTube videos, ArXiv papers, Wikipedia articles, Substack newsletters, RSS feeds, Google Docs, GitHub pages, and more. Returns Markdown with up to 63% fewer tokens than the raw source HTML.

Convert a file or URL to Markdown and return both content and structured metadata. Metadata includes title, estimated token counts for all major models, word count, character count, and reading time. Args: source: Either a URL (starting with http/https) or absolute file path source_type: Either "url" or "file". Default: "url" Returns: Markdown content with a metadata header block containing all stats

Extract the full transcript from any public YouTube video as clean Markdown. Works with standard watch links (youtube.com/watch?v=) and short links (youtu.be/). The video must have captions enabled — including auto-generated captions. Returns the transcript as flowing Markdown paragraphs, not raw caption fragments.

Count the exact number of tokens in a text string for a specific AI model. Uses tiktoken for OpenAI models and estimates for others. Args: text: The text to count tokens for model: The AI model to count tokens for. Options: gpt-4o, gpt-4o-mini, gpt-4.1, claude-sonnet, claude-haiku, gemini-pro, gemini-flash, llama-4, deepseek-v3, mistral-large. Default: gpt-4o Returns: Token count information including count, context window, and fit status

List all file formats and URL types that inktomd supports for conversion to Markdown. Use this to check whether a specific file type or URL source is supported before attempting conversion.

Convert a file or URL to Markdown, then split it into optimally-sized chunks ready for insertion into a vector database or RAG pipeline. Returns a JSON array of chunks with token counts, making this the single tool needed to go from raw document to RAG-ready data. Args: source: Either a URL (starting with http/https) or absolute file path source_type: Either "url" or "file". Default: "url" chunk_size: Target token count per chunk. Default: 512. Recommended range: 256-1024 overlap: Token overlap between consecutive chunks to preserve context. Default: 50 Returns: JSON array of chunks, each with: chunk_id, text, token_count, char_count