seedance-prompts-mcpSAFE
MCP server: 150 AI video prompts that were each rendered into a real video with Seedance 2 — search, inspect, audit and compose. Zero dependencies.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
150 AI video prompts that were each actually rendered into a video. Search them, read the full text in English and Japanese, watch the clip the prompt produced, audit your own draft against what the rendered prompts specify, or compose a new one — all from your MCP client.
Most "prompt library" packages ship prompts nobody ran, so you find out what a prompt does only after you spend a generation on it. Here the clip came first: every entry links to the video that this exact text produced, and the audit tool measures your draft against all 150 of them rather than against someone's opinion of good prompting.
Add it to your client with the two lines below, then ask it to find you a prompt.
Install
Node 18+. No dependencies, no API key, no network access at runtime — the prompt set is bundled.
{
"mcpServers": {
"seedance-prompts": {
"command": "npx",
"args": ["-y", "seedance-prompts-mcp"]
}
}
}Claude Desktop: claude_desktop_config.json. Cursor: .cursor/mcp.json. Any other stdio MCP client takes the same two lines.
Tools
Why the audit is worth running
The seven elements are not a style guide someone invented — they are cou
5d7897aa2709OBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add seedance-prompts-mcp -- npx -y [email protected]
Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
build_prompt | read | Compose a structured video prompt from parts. Fills the seven elements into the bracket format the rendered prompts use, and flags the parts you left empty. |
check_prompt | read | Audit a draft video prompt against the seven elements measured across the 150 rendered prompts (style, scene, subject, camera, lighting, sound, timeline). Returns what is missing, why it matters, and a real prompt to copy from. |
get_prompt | read | Full English and Japanese text of one prompt, plus the example video URL that this exact prompt produced. |
list_categories | read | The ten prompt categories with how many prompts each one holds. |
search_prompts | read | Search 150 AI video prompts that were each actually rendered into a video with Seedance 2. Returns titles, categories and source links; use get_prompt for the full prompt text and the example video. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
5d7897aa2709full audit observations/trust-audit/mcp-server/hanshs474__seedance-prompts-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 5d7897aa2709 | SAFE | B | 89 | first audit |
Questions
What is the seedance-prompts-mcp MCP server?
MCP server: 150 AI video prompts that were each rendered into a real video with Seedance 2 — search, inspect, audit and compose. Zero dependencies.
What tools does seedance-prompts-mcp expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is seedance-prompts-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does seedance-prompts-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does seedance-prompts-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as seedance-prompts-mcp at 1.0.1.
How current is this page?
The grade is for one exact copy of the source (5d7897aa2709), read on 2026-10-12. The repository is watched and re-audited when it changes.