A side-by-side look at the Runapi AI MCP and Seedance Prompts MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Runapi AI MCP for multimedia process work as a local process; choose Seedance Prompts MCP for multimedia process as a local process. You can also run both side by side in one mcpServers block.
list_models, get_model_info, list_actions.search_prompts, get_prompt, list_categories.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Multimedia Process | Multimedia Process |
| Quality signal | 68/100 · Great | 53/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 55 | 0 |
| Directory activity | 3 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 9 | 5 |
| Full listing | View Runapi AI MCP | View Seedance Prompts MCP |
list_modelsList RunAPI models from the embedded catalog. Optional filters: modality, service, or action.get_model_infoGet supported endpoint, current runtime pricing, and input constraints for a RunAPI model slug. Add service and action when the model supports multiple endpoints.list_actionsList RunAPI endpoint names grouped by output modality.check_pricingReturn current runtime pricing for a RunAPI model/action pair.search_promptsSearch RunAPI prompt examples by modality, category, tags, text query, model, or featured status. Free, no API key required.check_balanceReturn the authenticated RunAPI account balance and spending metrics.create_taskRun a RunAPI operation with a caller-generated idempotency key. Asynchronous operations can optionally poll until completion.get_taskFetch the current status and latest payload for an existing RunAPI task.loginAuthenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.search_promptsFree-text search over 150 prompts (English or Japanese), filter by category or by whether the prompt expects a reference image.get_promptFull English + Japanese prompt text, the example video URL, and where to run it.list_categoriesThe ten categories and how many prompts each holds.check_promptAudits a draft against the seven elements measured across all 150 rendered prompts — style, scene, subject, camera, lighting, sound, timeline. Names what is missing, why it matters, and hands you a real prompt to copy from.build_promptComposes those seven elements plus timeline beats into the bracket format the rendered prompts use, and tells you which fields you left to the model.Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"runapi-ai-mcp": {
"command": "npx",
"args": [
"-y",
"@runapi.ai/mcp"
]
}
}
}
{
"mcpServers": {
"seedance-prompts-mcp": {
"command": "npx",
"args": [
"-y",
"seedance-prompts-mcp"
]
}
}
}