Read-only MCP server over RealRun's published, independent tests of AI models on everyday tasks (inbox triage, meeting scheduling, receipts, finance). Ask "which model should I use for task X?" and get scores, a pick with alternatives, and safety warnings. Tools: list_tasks, get_
Prices and medians update for the tier you select.
Ranked by how closely each one matches realrun's job. Prices show each provider's Pro state; entry prices are labelled as such. Unpriced products still belong to the market.
Market = the products most similar to this one by capability; prices are median / quartiles over its priced members, separated by provider type and buyer tier.