Claude Code, Cursor, Codex & Grok commission a calibrated, cross-model-reviewed build spec — scored before you build, without leaving the loop. Connect your agent over MCP, or commission one in the browser.
house committee writes the spec · first run free · no card
Add one MCP server to Claude Code, Cursor, Codex, or Grok. Your agent commissions a calibrated spec, polls it to a reviewer-derived score, fetches the body, and can push it to a private GitHub repo — without leaving the editor.
{
"mcpServers": {
"sparkvibe": {
"url": "https://api.sparkvibeai.com/mcp",
"transport": "streamable-http",
"headers": {
"Authorization": "Bearer svai.YOUR_CREDENTIAL_ID.YOUR_SECRET"
}
}
}
}
commission_spec — dispatch the house committeeget_commission — poll to a scoreget_spec — pull the spec + quality signalspush_to_github — scaffold a private repoRead tools too: get_spec_body, get_subscription, and the pre-spec interview (start/answer/skip/get_interview).
real committee runs, cross-model reviewed and scored before any code — read all three in full on the showcase ▸