MCP server & CLI

Use every AI model from your agent or terminal.

OttoPort ships a Model Context Protocol server and a lightweight CLI so Claude Code, Cursor, scripts, and CI jobs can call the same GPT, Claude, Gemini, image, video, speech, and music models behind one API key.

Configure MCP Install CLI

One command surface

export OTTOPORT_API_KEY=gh_...
ottoport models --modality video
ottoport chat "summarize this in one sentence" --model claude-sonnet-5
ottoport image "product photo of a chrome torus" --model gpt-image-2
ottoport video "cinematic product reveal, black background" --model kling-3.0
ottoport speech "Welcome to OttoPort" --voice alloy --out welcome.mp3
ottoport music "lo-fi focus beat" --duration 20 --out focus.mp3
ottoport mcp

Agent-native

Expose OttoPort as MCP tools inside Claude Code, Cursor, and other MCP clients.

Scriptable

Use the CLI in shell scripts, CI jobs, dataset generation, and content pipelines.

One key

Use the same OttoPort API key for LLM, image, and video workloads.

MCP

Connect OttoPort to your coding agent.

Add OttoPort as an MCP server and your agent can list models, compare pricing, call chat models, and trigger image or video generation tools.

Client configuration

{
  "mcpServers": {
    "ottoport": {
      "command": "npx",
      "args": ["-y", "ottoport", "mcp"],
      "env": {
        "OTTOPORT_API_KEY": "gh_...",
        "OTTOPORT_BASE_URL": "https://ottoport.ai"
      }
    }
  }
}

ottoport_list_models

Discover chat, image, and video models with provider and pricing metadata.

ottoport_chat

Call GPT, Claude, and Gemini models from any MCP-compatible agent.

ottoport_generate_image

Generate or edit images with GPT Image and Nano Banana models.

ottoport_generate_video

Generate videos with Veo, Kling, Seedance, and Gemini video models.

ottoport_generate_speech

Synthesize speech with OpenAI, ElevenLabs, or Gemini voice models.

ottoport_generate_music

Generate music through the deployment's configured music gateway.

CLI

Run models from the terminal.

The CLI mirrors the public API: list models, call chat completions, generate images, submit video jobs, and synthesize audio without writing boilerplate.

npm install -g ottoport
export OTTOPORT_API_KEY=gh_...
ottoport models --modality video
ottoport chat "summarize this in one sentence" --model claude-sonnet-5
ottoport image "product photo of a chrome torus" --model gpt-image-2
ottoport video "cinematic product reveal, black background" --model kling-3.0
ottoport speech "Welcome to OttoPort" --voice alloy --out welcome.mp3
ottoport music "lo-fi focus beat" --duration 20 --out focus.mp3
ottoport mcp

Streams chat completions by default

Prints generated media URLs

Supports speech and music generation

Supports --json for model lists

Reads OTTOPORT_API_KEY and OTTOPORT_BASE_URL

Same API, more surfaces

Build with HTTP, SDKs, MCP, or CLI.

Start in the playground, automate in the terminal, then wire the same model IDs into your app.

Read API docs