AI & Machine Learning

tramsangtao.com

Provides access to AI generation API credits, model availability, and job status.

1 endpoint14 known toolsFirst detected September 2, 2026Last detected September 2, 2026

ENDPOINT 1

https://mcp.tramsangtao.com/mcp

No auth detected

MCP server metadata

Name: tramsangtao
Version: 2.14.7

Capabilities

experimentalprompts.listChangedresources.listChangedtools.listChangedtasks.listtasks.canceltasks.requests.tools.calltasks.requests.prompts.gettasks.requests.resources.read

Server instructions

tramsangtao.com AI generation API (Vietnamese market). Credits-based billing. Workflow: generate_image/generate_video returns a job_id immediately → call wait_for_job(job_id) until status=completed → use output_url. - wait_for_job timed_out=true is NORMAL for video — just call it again. - status=pending means queued behind your concurrency limit (see get_limits), not an error. - External images/videos/audio MUST be imported with upload_media_to_cdn (or the backward-compatible alias upload_from_url) before being used as generate inputs. - Call list_models before using a non-default model — catalog and pricing are live. - Check get_balance if unsure about credits. Never retry a generate call that timed out — check get_job first (retrying can double-bill).

Known tools 14

get_balance

Get the remaining credit balance for your API key.

Inferred read-only

get_limits

Get concurrency limits and currently active/queued job counts.

Inferred read-only

list_models

List available image/video models with live pricing and supported params.

Inferred read-only

list_llm_models

List LLM models available on llm_chat, with per-token credit pricing.

Inferred read-only

get_job

Check the status of a generation job (single request, no waiting).

Inferred read-only

wait_for_job

Poll a job until it finishes or max_wait_seconds elapses.

Inferred read-only

generate_image

Generate an image (text-to-image, or image-to-image when image_urls given).

Inferred read-only

generate_video

Generate a video from text (t2v) or reference image(s) (i2v).

Inferred read-only

generate_motion

Motion control: transfer motion from a reference video onto a character image.

Potential side effects

generate_kol_video

Generate a talking-avatar (KOL) video from an audio file + face image.

Inferred read-only

upload_from_url

Import an external media URL into the platform CDN.

Inferred read-only

upload_media_to_cdn

Upload/import external media into the platform CDN.

Potential side effects

extract_media

Extract direct media URLs (video/images) from a social post URL.

Potential side effects

llm_chat

Chat completion via the platform's LLM API (Gemini/GPT backends).

Inferred read-only

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.tramsangtao]
url = "https://mcp.tramsangtao.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "tramsangtao": {
      "type": "http",
      "url": "https://mcp.tramsangtao.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: tramsangtao
Remote MCP URL: https://mcp.tramsangtao.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": {
    "tramsangtao": {
      "url": "https://mcp.tramsangtao.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "tramsangtao": {
      "type": "http",
      "url": "https://mcp.tramsangtao.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "tramsangtao",
  "transport": "streamable-http",
  "url": "https://mcp.tramsangtao.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.