"Jupyter" matching MCP tools:

• convert_document_to_markdown

  Iteration Layer

  Convert a document or image to clean markdown. The file parameter must be an object with type, name, and either base64 or url. Returns name, mime_type, markdown, and description (images only). Use this when you need the full document content in markdown for summarization, search, or agent context. Use extract_document instead when you need typed structured fields. Supports PDF, DOCX, PPTX, ODT, ODS, XLSX, EPUB, RTF, LaTeX, images (PNG, JPG, GIF, WebP, AVIF, HEIF, BMP, TIFF, JP2), HTML, CSV, TSV, EML, MSG, Jupyter notebooks, and many text/markup formats. Email files (EML, MSG) include attachment extraction. Max file size: 50 MB.

  Connector

• extract_document

  Iteration Layer

  Extract structured data from documents using AI. The files parameter is an array of file objects, each with type, name, and either base64 or url. The schema parameter defines the typed fields to extract. Define a schema with typed fields (text, number, date, boolean, enum, email, IBAN, country, currency, address, arrays, calculated) and receive extracted values with confidence scores (0-1) and source citations. Use this when you need typed structured data. Use convert_document_to_markdown instead when you need the full document text first. Supports PDF, DOCX, PPTX, ODT, ODS, XLSX, EPUB, RTF, LaTeX, images (PNG, JPG, GIF, WebP, AVIF, HEIF, BMP, TIFF, JP2), HTML, CSV, TSV, EML, MSG, Jupyter notebooks, and many text/markup formats. Email files (EML, MSG) include attachment extraction. Use arrays with nested schemas for repeating data like invoice line items. Max file size: 50 MB per file.

  Connector

• recipes_search

  mcp

  Find a step-by-step setup recipe matching a user's intent — installing, configuring, or deploying anything on a Linux VM (web servers, databases, container runtimes, dev environments, networking, security tooling, ML stacks — any software setup an LLM agent might be asked to perform). ALWAYS call this FIRST when a user asks to set up, install, deploy, run, host, or spin up any service or software on a Massed Compute VM, BEFORE calling instances_launch. The recipe returned will include the correct VM size, image, and step-by-step instructions the user expects you to follow. Examples that should trigger this tool: 'I want an nginx reverse proxy', 'spin up a jupyter notebook', 'set up HTTPS for my app', 'install docker', 'load balance traffic across backends', 'protect my dashboard with a login', 'host a postgres database', 'serve a static site', 'run an ollama server'. If no recipe matches, recipes_search returns no results — that's a useful negative signal that the requested setup may need ad-hoc instructions, not a reason to skip calling this tool.

  Connector