Skip to main content
Glama
see-dance-2-prompt-mcp

see-dance-2-prompt-mcp

by gpt-img-2

See Dance 2 Prompt MCP

Deterministic, read-only MCP tools and an OpenClaw Skill for Seedance-oriented video prompt construction, multimodal reference planning, prompt diagnosis, and canonical See Dance 2 resource discovery.

This project does not generate media, call a model provider, access accounts, compare live pricing, or spend credits. See Dance 2 is independent and is not official ByteDance or Seedance documentation.

Install

npx -y github:gpt-img-2/see-dance-2-prompt-mcp

Related MCP server: opensora2-prompt-mcp

Tools

  • build_seedance_prompt

  • plan_reference_sequence

  • diagnose_seedance_prompt

  • get_see_dance_2_resources

OpenClaw

openclaw mcp add see-dance-2 \
  --command npx \
  --arg -y \
  --arg github:gpt-img-2/see-dance-2-prompt-mcp

The Skill source is in openclaw/see-dance-2-video-prompt-architect.

Development

pnpm install
pnpm validate

Canonical product resources: see-dance-2.com/llms.txt

Available Tools

4 tools
build_seedance_promptBuild a Seedance-oriented video promptB
Read-onlyIdempotent

Turn a rough idea into a deterministic English or Chinese prompt with separate subject and camera motion, exact reference bindings, and continuity controls.

Inputs: idea (required), avoid, lighting, workflow, +7 more.

diagnose_seedance_promptDiagnose a Seedance-oriented promptA
Read-onlyIdempotent

Check English or Chinese prompts for visible motion, camera direction, lighting, continuity, and preserved reference tokens.

Inputs: prompt (required).

get_see_dance_2_resourcesGet See Dance 2 resourcesB
Read-onlyIdempotent

Return canonical See Dance 2 prompting, workflow, reference, or safety resources without fetching external content.

Inputs: topic.

plan_reference_sequencePlan a reference-aware sequenceA
Read-onlyIdempotent

Create a deterministic 1–6 shot sequence with exact reference bindings, timing, continuity anchors, and end frames.

Inputs: idea (required), shotCount, cameraStyle, continuityAnchor, +2 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clear, distinct role: building a prompt, planning a sequence, diagnosing issues, and fetching resources. There is no overlap in purpose, making selection unambiguous.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern using snake_case, with clear action prefixes (build, plan, diagnose, get). The naming is uniform and predictable.

    Tool Count5/5

    Four tools is an appropriate scope for this domain, covering the core workflow without redundancy or excessive granularity. Each tool earns its place.

    Completeness5/5

    The toolset covers the full lifecycle: creating a prompt, planning sequences, diagnosing problems, and accessing resources. There are no obvious missing operations for the stated purpose.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables searching the public C Dance AI prompt gallery, inspecting complete prompts, comparing production workflows, and turning rough ideas into structured video prompt briefs.
      4
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables deterministic, read-only creation of bilingual video prompts, timed reference-aware shot plans, and focused prompt diagnostics without API keys or external provider calls.
      4
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Provides read-only tools to build English or Chinese video prompts, plan reference-aware sequences, diagnose prompts, and fetch canonical SeeVido resources without API keys.
      4
      MIT