Wan27 MCP
Generate AI images and videos, browse models, estimate credit costs and track tasks from Cursor, Claude or Codex. MIT-licensed stdio client. Requires Node.js 22+, macOS or Linux, and an active paid Wan27 subscription. First run wan27 auth login. Docs: https://wan2-7.io/mcp/ . Repository: https://github.com/NotUsingGithub/wan27-mcp
Ads
Installation
npm install -g @wan27/cli
Configuration
{
"mcpServers": {
"wan27": {
"command": "npx",
"args": [
"-y",
"@wan27/cli",
"mcp"
]
}
}
}Paste into ~/.cursor/mcp.json or .cursor/mcp.json
Related MCP servers
Multimedia Process
denisok-ai/magicmaster-mcp
Audio mastering for AI agents: LUFS/True Peak targets for Spotify and podcasts, Suno/Udio AI-fingerprint removal, mastering passport in chat (hosted server)
Multimedia Process
industriesfatty-spec/fattly-mcp
Generate AI images, video, voiceovers, avatars and UGC ads through 50+ models via fattly.app
Multimedia Process
musevate/MCP
Generate video from a prompt, from an image, or from up to thirty reference images, routed across the field of AI video models (Sora, Veo, Kling, Seedance, Hailuo, Wan and more). Quotes the credit cost before spending it, and refunds a technical failure automatically. Hosted remote server with OAuth, plus an MIT stdio bridge for clients that cannot speak streamable HTTP; requires a Musevate account.
Multimedia Process
gridhra/atx-mcp
Deterministic, non-generative image editing for agents: straighten, crop, mask, layer, apply LUTs, strip EXIF/GPS, and encode to WebP/AVIF/JPEG/PNG through declarative transform recipes. Originals are never modified, every result is an immutable revision with full lineage, and the same recipe reproduces byte-identical output on any machine. `npx -y atx-mcp --workspace /path/to/asset-workspace`
Multimedia Process
kimo
Video editor with no GUI that AI agents drive over MCP. Cut, trim, keyframe, colour grade, motion-track, key, relight, caption, mix audio and export, all through tool calls. One ~10 MB CPU-only Rust binary (kimo-mcp, stdio transport), MIT-licensed; needs ffmpeg/ffprobe. Works with Claude Code, Codex, Cursor and OpenCode. Repo: https://github.com/naman-sharma12345/kimo Site: https://getkimo.tech
Multimedia Process
Neume
Neume's MCP server lets ChatGPT, Claude, Cursor and any MCP client make full AI songs with vocals. Describe a song or paste lyrics and Neume makes it; change the words of one part (5-30 seconds) and it is sung again in the same voice, keeping the melody; reimagine any song in a new style. Tools: generate_song, get_song_details, get_my_songs, get_song_parts, change_lyrics, reimagine_song, get_balance, plus audio-upload tools. Remote Streamable HTTP endpoint https://api.neume.io/v1/mcp with OAuth 2.1 sign-in (Neume account); the assistant confirms before using credits. Docs: https://neume.io/blog/neume-mcp-server. By Neumosys LLC.
Multimedia Process
SHARProduction/production-metadata-mcp
[SHAR Production](https://sharprod.com/) AI-hybrid video-production metadata gate: read-only local stdio MCP that validates rights-aware production manifests and returns a releasability result. One tested tool; no API key, network calls, local-file access, or publishing operations. Install from source: `npm install && node server.js`.
Multimedia Process
verIdyia/autoeq-mcp
Headphone/IEM equalization database with 8,800+ models from AutoEQ. Search by name or sound signature, get parametric EQ settings, compare headphones band-by-band, and browse Harman preference score rankings. Includes automatic sound signature classification (Neutral, Warm, Bright, Dark, V-shaped, etc.).