Koskamo

multimodal-mcp

A community-driven MCP server that provides a unified interface for multi-provider media generation. It supports generating images, videos, and audio, as well as editing images and transcribing speech. It integrates with providers like OpenAI, xAI, Gemini, ElevenLabs, and BFL, allowing users to select specific providers per request and automatically saving output files to disk.

Package and access

Local package with source-attributed installation metadata. Koskamo does not execute packages during review.

multimodal-mcp logo, by rsmdtCommunity listingLocal stdioSource reviewed; not executedPublished by rsmdt
You need:Set the API key for at least one provider.
Vendor documentation

Checks and signals

Each line is separate evidence, not a trust score.

  • Popularity 2 GitHub stars

What you can do with it

  • Generate images from text prompts using OpenAI, xAI, Gemini, or BFL
  • Generate videos from text prompts using OpenAI, xAI, or Gemini
  • Create audio (TTS, sound effects) and transcribe speech using OpenAI or ElevenLabs
  • Edit images using OpenAI, xAI, Gemini, or BFL

Source and maintenance

Community listingRegistry 1.3.1MIT
mcp-registry: io.github.rsmdt/multimodal@1.3.1Source repository
Last repository push
Latest release
v1.4.0
Maintenance checked

Packages and installation

Source-provided package data. Koskamo has not executed or live-probed this package.

@r16t/multimodal-mcp 1.3.1

npm
@r16t/multimodal-mcp package definition
{
  "version": "1.3.1",
  "transport": "stdio",
  "identifier": "@r16t/multimodal-mcp",
  "registryType": "npm",
  "environmentVariables": [
    {
      "name": "OPENAI_API_KEY",
      "format": "string",
      "description": "OpenAI API key for image, video, audio generation and transcription"
    },
    {
      "name": "XAI_API_KEY",
      "format": "string",
      "description": "xAI API key for image and video generation"
    },
    {
      "name": "GEMINI_API_KEY",
      "format": "string",
      "description": "Google Gemini API key for image, video, and audio generation"
    },
    {
      "name": "ELEVENLABS_API_KEY",
      "format": "string",
      "description": "ElevenLabs API key for audio generation and transcription"
    },
    {
      "name": "BFL_API_KEY",
      "format": "string",
      "description": "BFL API key for FLUX image generation and editing"
    },
    {
      "name": "MEDIA_OUTPUT_DIR",
      "format": "string",
      "description": "Directory for saved media files (defaults to cwd)"
    }
  ]
}

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · repository · passed · metadata changed · updated
  • · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown

Connect from your client

Each snippet configures the same source-provided package; replace placeholders before use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Cursor

Merge this local stdio configuration, replace every placeholder environment value, and restart Cursor. Koskamo has not executed this package.
Cursor configuration
{
  "mcpServers": {
    "multimodal-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@r16t/multimodal-mcp@1.3.1"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "XAI_API_KEY": "<YOUR_XAI_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "ELEVENLABS_API_KEY": "<YOUR_ELEVENLABS_API_KEY>",
        "BFL_API_KEY": "<YOUR_BFL_API_KEY>",
        "MEDIA_OUTPUT_DIR": "<YOUR_MEDIA_OUTPUT_DIR>"
      }
    }
  }
}

Cline

Merge this local stdio configuration, replace every placeholder environment value, and restart Cline. Koskamo has not executed this package.
Cline configuration
{
  "mcpServers": {
    "multimodal-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@r16t/multimodal-mcp@1.3.1"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "XAI_API_KEY": "<YOUR_XAI_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "ELEVENLABS_API_KEY": "<YOUR_ELEVENLABS_API_KEY>",
        "BFL_API_KEY": "<YOUR_BFL_API_KEY>",
        "MEDIA_OUTPUT_DIR": "<YOUR_MEDIA_OUTPUT_DIR>"
      }
    }
  }
}

VS Code

Merge this local stdio configuration, replace every placeholder environment value, and restart VS Code. Koskamo has not executed this package.
VS Code configuration
{
  "servers": {
    "multimodal-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@r16t/multimodal-mcp@1.3.1"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "XAI_API_KEY": "<YOUR_XAI_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "ELEVENLABS_API_KEY": "<YOUR_ELEVENLABS_API_KEY>",
        "BFL_API_KEY": "<YOUR_BFL_API_KEY>",
        "MEDIA_OUTPUT_DIR": "<YOUR_MEDIA_OUTPUT_DIR>"
      }
    }
  }
}

Claude Desktop

Merge this local stdio configuration, replace every placeholder environment value, and restart Claude Desktop. Koskamo has not executed this package.
Claude Desktop configuration
{
  "mcpServers": {
    "multimodal-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@r16t/multimodal-mcp@1.3.1"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "XAI_API_KEY": "<YOUR_XAI_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "ELEVENLABS_API_KEY": "<YOUR_ELEVENLABS_API_KEY>",
        "BFL_API_KEY": "<YOUR_BFL_API_KEY>",
        "MEDIA_OUTPUT_DIR": "<YOUR_MEDIA_OUTPUT_DIR>"
      }
    }
  }
}

Let your agent find its tools

Find servers like multimodal-mcp from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 4,469