Medux MCP Server
OfficialThis server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Medux MCP Server
Connect AI assistants to Medux for AI media generation and editing: video, image, speech, voice cloning, avatars, and PDF/audio/video tools.
Endpoint (Streamable HTTP) |
|
Authentication | OAuth sign-in, or |
Tools | 60+ (generation, editing, conversion, account, task query) |
Endpoint change: the canonical endpoint is now
https://medux.io/mcp. The oldhttps://medux.io/api/mcp/v1still works, and existing API keys and OAuth grants stay valid.
Quick start by client
Client | Setup | Auth |
Codex |
| OAuth |
Claude Code |
| OAuth |
claude.ai / Claude Desktop | Customize → Connectors → Add custom connector → | OAuth |
Cursor | API key | |
VS Code / GitHub Copilot | see below | API key |
Step-by-step guides, tool overview and troubleshooting for Codex and Claude live in medux-mcp-examples.
Related MCP server: MiniMax MCP JS
Authentication
OAuth (recommended): clients register automatically (DCR) and use authorization code + PKCE. Sign in to Medux in the browser and approve access. Tokens grant only
mcp:tools, refresh automatically, and the authorization expires after 30 days.API key: create a key (starts with
sk-medux-) in your Medux account at https://medux.io and send it as a Bearer token. Keep it secret; never commit it.
GitHub Copilot / VS Code
Requires VS Code 1.99+ with GitHub Copilot signed in, and Copilot Chat in Agent mode.
Run MCP: Open User Configuration from the Command Palette (⇧⌘P / Ctrl+Shift+P).
Add the server:
{ "servers": { "medux": { "type": "http", "url": "https://medux.io/mcp", "headers": { "Authorization": "Bearer ${input:medux-api-key}" } } }, "inputs": [ { "type": "promptString", "id": "medux-api-key", "description": "Medux API key", "password": true } ] }In the MCP Servers list, open the gear next to
meduxand choose Start Server (or Restart Server).In Copilot Chat (Agent mode) open the tools picker and confirm the
meduxtools are listed.Try a harmless request first, for example: "Use medux to check my balance".
If the key prompt never appears (tool calls end with Canceled or 401), put the key directly in the header of your user-level mcp.json (never in a repository), then restart the server:
"headers": { "Authorization": "Bearer sk-medux-xxxxxxxx" }Troubleshooting
Symptom | Likely cause |
| Missing |
| The key prompt was not answered; use the direct-header form |
| The request reached Medux; the task or resource id does not exist |
Server not listed | Check the config saved correctly; view logs via the gear → Show Output |
Worked on | Remove the server and add it again with the new URL; re-authenticate |
Registry
Published to the MCP Registry as io.github.MeduxIO/medux
through .github/workflows/publish-mcp.yml (GitHub OIDC).
To release a new version: bump version in server.json, then run the workflow or push a v* tag.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
AI video, image and audio generation with 140+ AI models from any MCP agent
Direct AI video, image, music and storyboard production from any MCP client.
Generate images, video, audio and short films with 140+ AI models from any MCP client.
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI clients like Claude and ChatGPT to generate images and videos, animate images, create lip-synced videos, list TTS voices, and manage media via remote MCP tools.-
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible clients to generate images and videos, synthesize speech, clone and design voices, and create related media outputs.468 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible clients to generate images and videos, synthesize speech, clone and design voices, and dynamically configure API interactions.468 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible clients to generate images and videos, synthesize speech, clone voices, and design custom voices through integrated AI APIs, with configurable output modes and local or cloud transports.468 npmMIT