A performance marketer's run/fix/kill verdict for AI agents — ad creative, campaigns, targeting.
Your agent writes 100 ads an hour. This one says which 3 to run. · An MCP server (and REST API) that gives an AI agent a performance marketer's judgment: design a targeting strategy, audit a campaign build, gate an ad creative before spend, diagnose a live campaign. Each is a deterministic, server-verified verdict. · Works in every agent you already run · Kill a bad ad for a penny, not a “test budget.” · We show the grading, not just the grade · Ad creative scoring API: three steps from copy to verdict
| Type | MCP server |
| Section | MCP servers |
| Pricing | free |
| Platform | Command line |
| Systems | cli, api |
| Hosting | cloud |
| Install | mcp |
| Protocols | mcp |
| Site language | en |
| GitHub | dinosaur24/spendict-mcp |
| Launched | 2026-07-11 |