"Methods for Categorizing Images" matching MCP servers:

Enables filling uploaded document templates (DOCX/HWP/HWPX/PDF) with chatbot-generated content while preserving original formatting, tables, and images, and saving as files.

MCP server for Everhour time tracking with first-class Asana integration, enabling tasks lookup, time logging, timer control, and timesheet review.

Enables creating PowerPoint presentations by rendering HTML/CSS slides as full-slide images and exporting them to .pptx files, with a preview tool for visual checking before finalizing.

Local MCP server for PDF and photo tasks: merge, split, rotate and number PDFs, convert images to PDF, and inspect or strip hidden photo metadata (EXIF/GPS). Runs entirely on your machine — no uploads, no accounts, no API keys.

Render PDFs and images from HTML templates (Jinja2, Liquid, Handlebars) or Word and PowerPoint files through the Formfeed API, check data against a template's schema before rendering, and convert Office documents to PDF.

Enables conversion of files, HTML, and Markdown to PDF through natural language, using the FileToPDF API.

Enables an AI agent to host a shared folder or join an invite link as a participant in a collaborative editing session, reading, editing, and writing the files the room shares. Runs the same sync engine and wire protocol as editor clients, so an agent and a person or another agent converge on the same documents and see each other's changes.

An MCP server that lets AI models interact with Oracle Fusion Cloud HCM across its entire REST surface. It uses generic, schema-aware tools to dynamically discover licensed modules and resources without per-endpoint code.

Enables AI assistants to build and edit Google Slides presentations through natural language, including managing slides, text, shapes, images, tables, speaker notes, comments, thumbnails, and exporting to PDF or PPTX.

Enables AI assistants to read Tic lists, tasks, and task images through read-only database queries.

Enables generation of PDF documents from JSON specs or Markdown, supporting themes, tables, images, and other rich blocks.

Kontur Diadoc API for AI assistants: legally significant document exchange, signing, counteragents, machine-readable powers of attorney and docflow status. 114 methods, each with a read/write/destructive safety class.

Enables reading and analyzing Confluence documentation content through the Confluence REST API. Supports extracting and converting text, tables, code blocks, and images from Confluence pages for Q\&A and analysis.

Enables AI assistants to inspect and fill fillable PDF forms by exact field name, then render and OCR the resulting page to confirm every value is actually visible, returning verdicts of VISIBLE, INVISIBLE, RENDER-ONLY, or MISSING.

Enables Claude to browse, search, read, write, and export Microsoft OneNote content through Microsoft Graph, including viewing high-resolution screenshots/images, collecting pages for reports, and writing reports back to notebooks or sections.

Enables AI assistants to manage COR project management platform resources like projects, tasks, hours, clients, teams, and users through natural language.

Enables AI agents to read-only inspect an OmniFocus database, retrieving exact tasks and projects, Inbox roots, complete project hierarchies, tags, dates, notes and workload or review overviews. All access is read-only and bounded, with no mutation, write tools or sync triggers.

MCP server for AI-driven document creation, enabling generation of PowerPoint decks with consistent design themes and auto-generated images via ComfyUI.

Enables Claude to browse, search, and read Microsoft OneNote notebooks and pages as clean markdown, including viewing screenshots and images at high resolution or zoomed into regions. It also lets users collect pages into reports and write, append, or edit pages, sections, and notebooks, and export original-resolution images and attachments locally.

Upload Markdown to Confluence with auto-converted Mermaid diagrams, code blocks, images, and tables. Supports creating, updating, and syncing pages.

Converts Markdown documents to professional Word documents with advanced formatting capabilities including mathematical formulas, custom styling, tables, images, headers/footers, and watermarks.

Enables AI agents to search, create, and manage Notion pages and databases through the Model Context Protocol. It features file-based operations and response extraction to optimize token usage and context efficiency.

Enables Claude to build and modify slide decks with bullets, pictures, charts, tables, speaker notes, themes and transitions, then export them as PowerPoint pptx, PDF, per-slide images or outlines. It also reads and inspects existing presentations, finding and replacing content across whole folders, and can optionally open decks in the DeckCraft app for live editing.

Enables MCP clients like WorkBuddy to inspect, edit, and publish Tencent Docs native collection forms, supporting question types such as short answer, single choice, multiple choice, and dropdown selections. It verifies drafts after writing and checks published versions without login cookies.

Enables harvesting assets from Apple Keynote decks, including PDF export, previews, extractable text, embedded images, and manifests through MCP resources and tools.

Enables AI agents to create, edit, and manage Microsoft PowerPoint presentations locally, including slides, text, and images, without requiring Microsoft Office.

Enables local MCP-based interactions with Google Docs, including bounded reading, private document creation, Markdown publishing, revision-safe exact text edits, and Persian RTL formatting.

Enables Claude to read, search, organize, and draft email in an Outlook/Microsoft 365 mailbox via Microsoft Graph, while pseudonymizing personal data (names, emails, phone numbers, national ID numbers, IBANs, addresses) into reversible tokens before anything reaches the model. Supports folder listing, message search, flagging, categorizing, moving, and draft creation/editing, but cannot send mail since it only requests Mail.ReadWrite and User.Read permissions.

Enables AI agents to create and manage ExcaliDash drawings through MCP by creating drawings, editing shapes and text, connecting elements, adding images, and organizing drawings into collections.

Well-designed PDFs from a single prompt. Describe what you need, get a professional document.