multimodal for VS Code
io.github.rsmdt/multimodal
Multi-provider media generation — images, video, audio, and transcription via a unified interface
client:VS Code
transport:stdio
runtime:npm
Install multimodal in VS Code
.vscode/mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "openai-api-key",
"description": "OPENAI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "xai-api-key",
"description": "XAI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "gemini-api-key",
"description": "GEMINI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "elevenlabs-api-key",
"description": "ELEVENLABS_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "bfl-api-key",
"description": "BFL_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "media-output-dir",
"description": "MEDIA_OUTPUT_DIR",
"password": true
}
],
"servers": {
"multimodal": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@r16t/multimodal-mcp"
],
"env": {
"OPENAI_API_KEY": "${input:openai-api-key}",
"XAI_API_KEY": "${input:xai-api-key}",
"GEMINI_API_KEY": "${input:gemini-api-key}",
"ELEVENLABS_API_KEY": "${input:elevenlabs-api-key}",
"BFL_API_KEY": "${input:bfl-api-key}",
"MEDIA_OUTPUT_DIR": "${input:media-output-dir}"
}
}
}
}VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs