"Examples of DeepSeek-related applications or projects" matching MCP servers:

Enables MCP-compatible agents to access KaiRouter's video generation API, providing tools to list available video models, generate videos (text-to-video or image-to-video) asynchronously, check job status, and list recent jobs.

Provides image understanding capabilities for MCP clients (e.g., Claude Code) by analyzing images using vision models from providers like Alibaba Cloud Bailian, OpenAI, or OpenRouter, returning detailed descriptions in Markdown format.

Hosted multi-model AI media + chat MCP server. Generates images, video, audio, face-swaps and talking-avatars, and chats across 300+ models (Claude, GPT, Gemini, DeepSeek…) - all from one balance and one API key.

Local MCP server that adds multimodal capabilities to text-only models like Codex/DeepSeek, offering tools for image description, audio transcription, video analysis, image/video generation, and speech synthesis.

A modular suite of MCP servers for Audiokinetic Wwise, enabling AI agents to browse, edit, audition, profile, and build Wwise projects through the Wwise Authoring API.

An MCP server that reads and builds CapCut projects locally, enabling natural language queries about project contents, missing media, and creation of new edits including beat-synced cuts.

Enables reading and creating projects in a local CapCut draft library through natural language — listing timelines, checking for missing media, and generating new edits from clips, with cuts automatically matched to the beat of a track. It works by cloning an existing draft as a structural template, so new projects inherit CapCut's undocumented file format.

An MCP server that assembles CapCut International projects by reading and writing local project files, adding captions, subtitles, overlays, and more so editors start with a mostly-done timeline. It includes tools for inspecting projects, restyling captions, importing subtitles, and rendering alpha-channel overlays via Remotion.

A professional implementation of a Model Context Protocol server that enables integration between DaVinci Resolve video editing software and AI assistants like Claude Desktop or Cursor.

Enables local control of Adobe After Effects via MCP, offering offline creative skills, project inspection, and operation execution without cloud relay or an installed AE panel.

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.

An MCP server that gives Claude Code (or any MCP client) full control of Reaper.

Enables creating real Scratch 3 projects from natural language prompts, producing editable .sb3 files with sprites, scripts, sounds, and backdrops.

Enables creating, inspecting, validating, and rendering NES FamiStudio .fms projects from plain JSON without a GUI.

Lets Codex inspect, build, wire, tune, sample, and visually verify running TouchDesigner projects for generative visuals, audio-reactive systems, and fast agent-assisted prototyping.

Enables programmatic creation and editing of JianYing Pro (剪映) draft projects through 12 deterministic MCP tools, covering asset placement, text, subtitles, audio tracks, draft saving, SRT export, and media probing. Produces structured, reproducible results without code generation or GUI automation.

A mock-first MCP server for audio generation that creates placeholder WAV files locally, enabling development and testing of audio workflows without APIs or costs.

Enables agents to manage video composition projects, run linting, render videos, capture snapshots, and monitor/cancel long-running jobs via MCP.

Enables AI assistants to fully control CapCut video editing projects, including creating projects, importing media, adding text/subtitles, managing audio, and editing timelines.

Extracts transcripts or spoken captions from multi-platform video links (Bilibili, YouTube, Douyin) and returns concise Markdown summaries or full transcripts, saving tokens by keeping full text out of the conversation.