Skip to main content
Glama

Turbogen MCP server

Generate images, video and audio with Turbogen straight from Claude Desktop, Claude Code, Cursor or any other MCP client. Same models and prices as the studio; credits come from your balance.

Tools

Tool

What it does

list_models(kind?)

Model ids, aspect/voice choices, options and credit prices (kind = image, video or audio)

generate_image(prompt, model="nano-banana-2", aspect="1:1", option?, reference_images?)

Image, saved locally; a preview is returned when the file is under 1 MB

generate_video(prompt, model="veo-3.1-fast", aspect="16:9", option="8s", image_path?)

Video clip; pass image_path for image-to-video

generate_audio(text_or_prompt, model="voice", aspect?, option?, lyrics?)

voice (aspect = voice name), music (aspect = Instrumental / With vocals + lyrics) or sfx

upscale_image(path, scale="2x")

Upscale a local image 2x or 4x

get_balance()

Remaining credits

job_status(job_id, download=false)

Status of a job, e.g. one that took longer than the 10-minute wait

Generation tools submit the job, poll every 5 s for up to 10 minutes (parallel jobs share one status request and wait out rate limits), download the result into the output folder and return the local path, the cost and your remaining credits.

Related MCP server: MiniMax MCP JS

Get an API key

API access comes with the Boost, Turbo and Max packs. Open API in the studio (https://turbogen.app/#/apikeys), create a key and copy it (lk_..., shown only once).

Configuration

Variable

Required

Default

TURBOGEN_API_KEY

yes

—

TURBOGEN_BASE_URL

no

https://turbogen.app

TURBOGEN_OUTPUT_DIR

no

~/Downloads/turbogen

Install

With uv nothing needs installing up front, uvx runs it on demand:

uvx turbogen-mcp

Or install the command once with pipx (or uv tool):

pipx install turbogen-mcp      # or: uv tool install turbogen-mcp
turbogen-mcp                            # waits for an MCP client on stdin; Ctrl+C to quit

Plain venv:

python -m venv .venv
.venv/bin/pip install turbogen-mcp     # Windows: .venv\Scripts\pip install turbogen-mcp

Requires Python 3.10+.

Claude Desktop

Edit claude_desktop_config.json (Settings > Developer > Edit Config; macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\) and restart Claude Desktop:

{
  "mcpServers": {
    "turbogen": {
      "command": "uvx",
      "args": ["turbogen-mcp"],
      "env": {
        "TURBOGEN_API_KEY": "lk_your_key_here"
      }
    }
  }
}

With pipx use "command": "turbogen-mcp" and drop args. If the app cannot find the command, give the full path (e.g. C:\\Users\\you\\.local\\bin\\turbogen-mcp.exe).

Claude Code

claude mcp add turbogen --env TURBOGEN_API_KEY=lk_your_key_here -- uvx turbogen-mcp
# installed with pipx instead:
claude mcp add turbogen --env TURBOGEN_API_KEY=lk_your_key_here -- turbogen-mcp

Add --scope user to make it available in every project. Check with claude mcp list.

Cursor

Create .cursor/mcp.json in the project (or ~/.cursor/mcp.json for all projects):

{
  "mcpServers": {
    "turbogen": {
      "command": "uvx",
      "args": ["turbogen-mcp"],
      "env": {
        "TURBOGEN_API_KEY": "lk_your_key_here",
        "TURBOGEN_OUTPUT_DIR": "~/Downloads/turbogen"
      }
    }
  }
}

Try it

Ask your assistant things like:

  • "List the Turbogen video models and their prices."

  • "Generate a 16:9 image of a lighthouse at dusk with nano-banana-2."

  • "Turn ~/Downloads/turbogen/lighthouse.png into an 8 second Veo clip with a slow push-in."

  • "Make a 5 second sound effect of waves on rocks."

  • "How many credits do I have left?"

Errors

  • Not enough credits (402): top up at <base>/#/pricing.

  • Invalid API key (401): the key is wrong, revoked, or the account has no API access.

  • Model unavailable (503): try another model or retry later.

  • Rate limited (429): up to 30 jobs per minute and 3 running at once.

  • Failed generations are refunded automatically.

Available Tools

7 tools
generate_audioA

Generate audio (voiceover, background music, a song or a sound effect) and save it locally.

text_or_prompt: for "voice" the text to speak; for "music"/"song"/"sfx" a description of the sound. model: "voice" (text to speech), "music" (instrumental background), "song" (sung, needs lyrics) or "sfx". aspect: the voice for "voice" (e.g. "Deep narrator", "Warm female"), the mood for "music" (e.g. "Cinematic", "Lo-fi"), the vocal for "song" ("Female vocal", "Male vocal", "Duet"); defaults to the first choice. See list_models(kind="audio"). option: length/duration, e.g. "300 chars" for voice, "30s" for music, "60s" for song, "5s" for sfx; defaults to the first. lyrics: song lyrics, required for "song".

Inputs: text_or_prompt (required), model, aspect, lyrics, +1 more. Returns: result

generate_imageA

Generate an image and save it locally. Returns the file path, cost and remaining credits (plus a preview).

prompt: what to draw. model: image model id (see list_models(kind="image")), default nano-banana-2. aspect: aspect ratio, e.g. "1:1", "16:9", "9:16". option: resolution/quality option such as "1K", "2K", "4K"; defaults to the model's first (cheapest) option. reference_images: optional list of local PNG/JPEG/WEBP paths used as references.

Inputs: prompt (required), model, aspect, option, +1 more.

generate_videoA

Generate a video clip and save it locally. Returns the file path, cost and remaining credits.

prompt: the shot - subject, action, camera move, light. model: video model id (see list_models(kind="video")), default veo-3.1-fast. aspect: "16:9", "9:16" (some models also "1:1" etc.). option: duration such as "4s", "6s", "8s"; must be one the model offers. image_path: optional local image for image-to-video (first frame / reference). Video takes 1-5 minutes; the call waits up to 10 minutes.

Inputs: prompt (required), model, aspect, option, +1 more. Returns: result

get_balanceA

Show the remaining credit balance of the account behind TURBOGEN_API_KEY.

Inputs: no named parameters. Returns: result

job_statusA

Check a generation job by id (e.g. one that outlived the 10-minute wait).

download: if true and the job is done, save its file to the output folder and return the path.

Inputs: job_id (required), download. Returns: result

list_modelsA

List available generation models with their ids, aspect/voice choices, options and credit prices.

kind: optional filter - "image", "video" or "audio".

Inputs: kind. Returns: result

upscale_imageA

Upscale a local image 2x or 4x and save the result next to other outputs.

path: local PNG/JPEG/WEBP file. scale: "2x" or "4x".

Inputs: path (required), scale.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool maps to a distinct action and resource: discovery (list_models), generation per media type (image/video/audio), upscaling, balance check, and async job lookup. The media-type split between generate_image, generate_video, and generate_audio is explicit in the names, so an agent can select correctly without reading descriptions in depth.

    Naming Consistency4/5

    Six of seven tools follow a clean snake_case verb_noun pattern (list_models, generate_image, generate_video, generate_audio, upscale_image, get_balance). The outlier is job_status, which drops the verb (a get_job_status form would be fully consistent), but it remains clearly readable.

    Tool Count5/5

    Seven tools is well-scoped for a media generation server: one per output modality, plus the necessary supporting operations (model catalog, balance, async job status). No tool feels redundant or like filler.

    Completeness4/5

    The surface covers discovery, generation for all three modalities, upscaling, cost/balance visibility, and recovery from timed-out jobs via job_status with download. Minor gaps remain: no job listing/cancellation, no image edit/variation operation, and no separate download/fetch tool for arbitrary job ids beyond job_status.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers