"Read the Docs" matching MCP servers:

File conversion for AI agents: office docs to PDF, PDF to Word, document interchange (Markdown/HTML/EPUB/LaTeX), and audio/video transcodes via the hushvert hosted API. Tools: convert_file, convert_poll, list_formats, check_usage.

Enables AI assistants to search, generate, and manipulate u-he synth presets through natural language, including browsing libraries, randomizing presets, and merging multiple presets.

Extract content from URLs, documents, videos, and audio files using intelligent auto-engine selection. Supports web pages, PDFs, Word docs, YouTube transcripts, and more with structured JSON responses.

Enables control of a local Sonic Pi runtime to run code, stop jobs, read events, and search docs/samples/synthdefs via OSC messages.

An open-source agent toolkit that auto-syncs SDK versions, docs, and examples—built for seamless integration with LLMs, and AI agents ( MCP compatible).

Enables AI agents to migrate YouTube channels to Rad TV, including planning migrations, running transfers, checking status, retrying failures, and managing HD token setup.

A local-first MCP adapter for Vicon Shogun Post that provides read-only inspection of motion-capture scenes, including subject markers and trajectory queries via the official SDK.

Enables executing Python scripts, rendering scenes, and controlling 3D objects in Blender via Claude, with support for Cycles and EEVEE engines.

A self-hosted MCP server that connects AI clients to local media-generation backends like ComfyUI and Blender, and provides built-in utilities for video/audio analysis, editing, subtitles, speech, and scene detection via a persistent file cache.

Lets any LLM agent actually watch videos: a watch_video tool takes a URL or local file and returns scene-aware keyframes fused with a timestamped transcript, processed 100% locally with per-source caching.

Unofficial MCP server for RØDECaster Pro II, providing tools to read and write audio processing parameters like noise gate, compressor, and routing, enabling AI agents to control the mixer.

Enables AI agents and terminals to generate images, video, and audio using 141 models from 28 providers via the Picsart gen-ai API.

Provides tools to read PDFs, extract images, convert between PDF and DOCX, create DOCX from text, and generate PDFs from DOCX, text, or HTML.

MCP server that enables AI agents to read and edit Ableton Live sets, including tracks, clips, MIDI notes, devices, and scenes.

Hosted Streamable HTTP MCP server (https://epublys.com/mcp) with 9 tools for EPUB/PDF manipulation: merge, split, compress, EPUB↔PDF conversion, metadata read/edit, validation with auto-fix, and AI cover generation. Free API key, no install. Listed on the official MCP registry as com.epublys/epublys.

Enables AI agents to search and read screen recordings from Clipy, including transcripts, AI summaries, and key moments with frames.

Enables AI-assisted, read-only inspection of local CapCut desktop projects by discovering the draft store, listing projects, and examining timeline structure, tracks, segments, canvas, FPS, and timing. It also checks CapCut compatibility before any editing.

A local MCP server bridging Bitwig Studio for agent-assisted music workflows, read-only by default with configurable write-policy gates.

A powerful MCP tool for parsing and manipulating MIDI files that allows users to read, analyze, and modify MIDI files through natural language commands, supporting operations like reading file information, modifying tracks, adding notes, and setting tempo.

Enables audio file analysis using Google's Gemini multimodal models with support for additional context and system instructions to guide the model's behavior.