Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/gpt-img-2/cdance-prompt-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/gpt-img-2/cdance-prompt-mcp/cdance-prompt-mcp)<a href="https://agentmods.dev/mcp/gpt-img-2/cdance-prompt-mcp/cdance-prompt-mcp"><img src="https://agentmods.dev/badge/mcp/gpt-img-2/cdance-prompt-mcp/cdance-prompt-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/gpt-img-2/cdance-prompt-mcp/cdance-prompt-mcp"><img src="https://agentmods.dev/badge/mcp/gpt-img-2/cdance-prompt-mcp/cdance-prompt-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cdance-prompt-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{ "cdance-prompt-mcp": { "command": "npx", "args": [ "-y", "cdance-prompt-mcp" ] } }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 9 lines scan A f01133487fd6
cdance-prompt-mcp is an MCP server published in the GitHub repository gpt-img-2/cdance-prompt-mcp (0 stars, last pushed 17d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
chinavideoai-prompt-mcp
MCP server "chinavideoai-prompt-mcp" as configured in gpt-img-2/chinavideoai-prompt-mcp. Runs locally from the chinavideoai-prompt-mcp npm package.
see-dance-2-prompt-mcp
MCP server "see-dance-2-prompt-mcp" as configured in gpt-img-2/see-dance-2-prompt-mcp. Runs locally from the see-dance-2-prompt-mcp npm package.
image3-prompt-mcp
MCP server "image3-prompt-mcp" as configured in gpt-img-2/image3-prompt-mcp. Runs locally from the image3-prompt-mcp npm package.
opensora2-prompt-mcp
MCP server "opensora2-prompt-mcp" as configured in gpt-img-2/opensora2-prompt-mcp. Runs locally from the opensora2-prompt-mcp npm package.
seevido-prompt-mcp
MCP server "seevido-prompt-mcp" as configured in gpt-img-2/seevido-prompt-mcp. Runs locally from the seevido-prompt-mcp npm package.
codex-control-plane-mcp
Durable MCP control plane for long-running Codex Desktop tasks. Runs locally from the codex-control-plane-mcp Python package.