Medux

io.github.MeduxIOPublished by GitHub account MeduxIOv0.1.1Updated Oct 30, 2026

AI video, image, speech, voice cloning and avatar generation, plus PDF/audio/video editing tools.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowMedia & Design

Overview

AI-generated overview

Medux is a remote MCP server that lets an assistant generate and edit AI video, images, speech, cloned voices, avatars, and PDF/audio/video files.

What you can do
  • Generate AI media: video, images, speech, cloned voices and avatars
  • Edit and convert media, including PDF, audio and video tools
  • Query generation and editing tasks by id
  • Work with 60+ tools covering generation, editing, conversion and task lookup
When to use it
Useful when you want an assistant to produce or transform media assets — a video clip, image, voiceover, avatar, or a converted PDF/audio/video file — without leaving the chat, and you already have a Medux account.
Requirements
A remote streamable HTTP endpoint at medux.io; no local package. A Medux account and API key (starts with sk-medux-) sent as an Authorization Bearer token, either through a prompted input or directly in the user-level MCP configuration. Network access to medux.io.
Before you install
The API key is a secret: keep it out of repositories and prefer a prompted input over hardcoding it in a shared config. Tool calls send requests to Medux's servers and may consume account credits or create media on your account; start with a harmless request to confirm the tools work. A 401 usually means a missing Bearer prefix or a wrong/revoked key.

Installation

In SourceWeft

  1. Open Medux in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.MeduxIO%2Fmedux/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "medux": {
      "type": "http",
      "url": "https://medux.io/api/mcp/v1"
    }
  }
}

README

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): https://medux.io/api/mcp/v1
  • Authentication: Authorization: Bearer sk-medux-...
  • Tools: 60+ (generation, editing, conversion, task query)

1. Get an API key

Create an API key (starts with sk-medux-) in your Medux account at https://medux.io. Keep it secret; do not commit it to a repository.

2. GitHub Copilot / VS Code

Requires VS Code with GitHub Copilot signed in, and Copilot Chat in Agent mode.

  1. Run MCP: Open User Configuration from the Command Palette (⇧⌘P / Ctrl+Shift+P).

  2. Add the server:

    json
    {  "servers": {    "medux": {      "type": "http",      "url": "https://medux.io/api/mcp/v1",      "headers": { "Authorization": "Bearer ${input:medux-api-key}" }    }  },  "inputs": [    { "type": "promptString", "id": "medux-api-key", "description": "Medux API key", "password": true }  ]}

  3. In the MCP Servers list, open the gear next to medux and choose Start Server (or Restart Server).

  4. In Copilot Chat (Agent mode) open the tools picker and confirm the medux tools are listed.

  5. Try a harmless request first, for example: "Use medux to list what you can do".

If the key prompt never appears

In some setups VS Code does not show the ${input:...} prompt, and tool calls end with Canceled or 401. Replace the header value with your key directly in your user-level mcp.json (never in a repository):

json
"headers": { "Authorization": "Bearer sk-medux-xxxxxxxx" }

Then restart the server.

Troubleshooting

SymptomLikely cause
401 / unauthorizedMissing Bearer prefix, wrong or revoked key
Canceled: Canceled on every callThe key prompt was not answered; use the direct-header form above
404 with NOT_FOUNDThe request reached Medux; the task or resource id does not exist
Server not listedCheck MCP: Open User Configuration saved correctly; view logs via the gear → Show Output

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

Source: README.md at commit cf7aee6

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.1.1LatestOct 23, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts