Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ARK_API_KEYYesYour BytePlus ModelArk API key, created under API Key Management after activating the Seedance and Seedream models.
ARK_BASE_URLNoModelArk endpoint.Singapore
SEEDANCE_APPROVALNoApproval mode: auto (dialog, else chat), dialog, chat, or off (track only). Equivalent to the --approval flag.auto
SEEDANCE_BUDGET_USDNoAsk before anything that crosses this budget amount. Equivalent to the --budget flag.20
SEEDANCE_OUTPUT_DIRNoSave every finished video and image here. Equivalent to the --output-dir flag.
SEEDANCE_IMAGE_MODELNoDefault image model.pro
SEEDANCE_PRICES_FILENoPath to a JSON file with extra or corrected prices.
SEEDANCE_VIDEO_MODELNoDefault video model.mini
SEEDANCE_HARD_CAP_USDNoNever spend past this amount in a period. Equivalent to the --hard-cap flag.
SEEDANCE_ASK_ABOVE_USDNoAsk before any single generation above this dollar amount. 0 asks every time. Equivalent to the --ask-above flag.0.50
SEEDANCE_BUDGET_PERIODNoThe period the budget applies to: day, week or month. Equivalent to the --period flag.month

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
generate_videoC

Make a Seedance video (text-to-video, image-to-video, or with reference media). Priced and checked by the spend guard before anything is sent.

generate_imageC

Make an image with Seedream. Priced and checked by the spend guard first.

video_taskC

Status of a video task. When it has succeeded: video_url, real cost, saved file.

list_video_tasksB

Recent video tasks on this key, newest first, with what each one cost.

cancel_video_taskA

Cancel a queued video task. Running tasks can't be stopped.

estimate_costB

Price a plan in dollars without spending anything.

preapprove_spendA

Get one human approval for a whole batch. Returns an approval_id to pass to each generate call; it covers up to the approved dollars and number of calls for 3 hours.

spend_statusA

What you've spent this period, by model, against your budget and caps.

check_setupB

Check the API key, the connection, and how spend approvals will reach the user.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 9 tools

Disambiguation4/5

Most tools target distinct actions (generate, cancel, estimate, check), and the spend trio of estimate_cost/spend_status/preapprove_spend is clearly differentiated by description. The only mild overlap is video_task (single status) versus list_video_tasks (batch listing), which descriptions resolve adequately.

Naming Consistency4/5

Snake_case is used throughout and most names follow a verb_noun pattern (generate_video, cancel_video_task, estimate_cost, check_setup). Minor deviations are the noun-phrase names video_task and spend_status, which read less like actions than their peers.

Tool Count5/5

Nine tools is well-scoped for a media-generation service with spend controls, covering generation, task lifecycle, and cost management without redundancy. Each tool earns its place.

Completeness4/5

The surface covers generation (video/image), task lifecycle (status, list, cancel), and the full cost-approval loop, which is strong coverage. A minor gap is the asymmetry where video tasks have status/list/cancel lifecycle but images have no equivalent task-status tool.

Maintenance

ActivityMaintained
ResponsivenessNo issues