Enables AI agents to generate editable PPTX presentations and standardized Word simulation reports with format confirmation, asynchronous task processing, semantic revision, and secure file download via MCP.
Enables AI agents to read and analyze PDF documents for natural language Q\&A. Supports multiple LLM providers including Google Gemini, Anthropic Claude, and OpenAI.
Enables PDF document processing including text, image, and table extraction, as well as intelligent classification and similarity analysis across multiple languages.
An MCP server that exposes Marker for high-quality PDF OCR and conversion, providing a tool to convert PDFs to markdown, JSON, or HTML with optional LLM-enhanced mode.
An intelligent PDF translation assistant specializing in academic papers with mathematical formulas, enabling context-aware translation with layout preservation.
Enables local LLMs to match lesson summaries or syllabus topics against PDF textbooks and manuals, returning the exact page ranges relevant to each topic along with brief explanations of why they matter. Runs entirely offline via Ollama embeddings and reasoning plus Tesseract OCR for scanned or image-only pages, so multi-hundred-page documents can be searched privately without API keys or cloud credits.
Provides Dify apps with a secure, app-scoped MCP tool catalog and action gateway for authorized FlowFlox operations, enabling intent-driven planning and fixed operational processes without exposing global credentials.
Free Industry 4.0 / IIoT tools, no API key or account: lint MQTT Sparkplug B topics, check a Unified Namespace (UNS) for naming and hierarchy problems, and run an industrial AI-readiness diagnostic for manufacturing digital transformation and smart-factory projects. Works in Claude Code, Codex and any MCP client.
Local, read-only MCP tools for B2B outreach: French telemarketing consent validity (décret 2026-662), GDPR gap report for customer service outsourced outside the EU, cost per kept meeting by lead source, and least-cost capable model selection.
Provides five safe tools (calc, search, model_drift, compare_runs, grade_answer) for arithmetic, keyword search, model drift monitoring, eval comparison, and answer grading against sources, all implemented directly from the MCP spec with zero dependencies.