← Registry

AI & Machine Learning

turbomaxai.com

An MCP server for browsing AI media models, estimating generation costs, and starting and tracking image, video, and audio generation tasks.

1 endpoint13 known toolsFirst detected November 3, 2026Last detected November 3, 2026

ENDPOINT 1

https://turbomaxai.com/mcp

No auth detected

MCP server metadata

Name
turbomax-ai
Version
1.0.0
Capabilities
toolsresources
Server instructions

TurboMax AI generates images, video and audio and answers chat, billed in prepaid credits from the user's wallet. Workflow: list_models -> (estimate_cost) -> generate_media -> get_task with waitSeconds until status is "completed" -> use resultUrl. For image-to-video / image-to-image / editing: upload_source_media first and pass the returned url as sourceImageUrl. Rules: generate_media and chat SPEND CREDITS. Always pass maxCredits to generate_media when acting without a human in the loop; the server refuses before charging if the cost is higher. Never invent a prompt for the user - use their words. A failed or cancelled job is refunded automatically. A read-only API key can browse and poll but cannot spend; a "generate" key can.

Known tools 13

list_models

List the image, video and audio models with what each accepts (tasks, aspect ratios, resolutions, duration range, modes) and its price in credits.

Inferred read-only
get_model

Full parameter details and pricing for one media model.

Inferred read-only
estimate_cost

Approximate credits for a media generation from the live price list.

Inferred read-only
generate_media

Start a generation.

Inferred read-only
get_task

Status, progress and result of a job started with generate_media.

Inferred read-only
cancel_task

Stop a job that is still processing and refund its hold.

Potential side effects
retry_task

Re-run a failed or cancelled job as a new job.

Inferred read-only
upload_source_media

Upload an image, video or audio file (PNG, JPEG, WebP, GIF, MP4, WebM, MOV, MP3, WAV) to use as sourceImageUrl in generate_media.

Potential side effects
list_chat_models

The text/chat models available to chat, with the default and whether each is currently available.

Inferred read-only
chat

Send one chat turn to a TurboMax text model and return its reply.

Potential side effects
get_wallet

Credit balance, credits-per-dollar, today's usage against the account limits, and recent ledger entries.

Inferred read-only
list_generations

The account's generation history, newest first, with status, cost and result links.

Inferred read-only
browse_gallery

Work other users chose to publish, with the prompt and model used.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.turbomax-ai]
url = "https://turbomaxai.com/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "turbomax-ai": {
      "type": "http",
      "url": "https://turbomaxai.com/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: turbomax-ai
Remote MCP URL: https://turbomaxai.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "turbomax-ai": {
      "url": "https://turbomaxai.com/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "turbomax-ai": {
      "type": "http",
      "url": "https://turbomaxai.com/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "turbomax-ai",
  "transport": "streamable-http",
  "url": "https://turbomaxai.com/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.