"Affinity" matching MCP servers:

Exposes two Qloo-grounded tools, resolve_taste_anchor and recommend_for_group, so any agent can turn what individual people like into per-person signals instead of stereotypes. Group picks are ranked by how many people each option covers, then by affinity, letting agents answer 'what should this group do?' with grounded recommendations.

Exposes Qloo taste-graph analysis of a restaurant's audience as MCP tools, letting existing agents retrieve a restaurant's entity, cross-domain affinities, over-indexing dishes and vibes, and demographic skew, or generate a fully verified weekly playbook of menu moves, events, and campaigns. Enables agents to ground restaurant decisions in Qloo evidence with affinity scores and an evidence ledger.

An MCP endpoint exposing find_regular_spots, build_connection_plan, and explain_match so agents can surface real nearby venues matched to a user's tastes via the Qloo taste graph, assemble a tiered six-week connection plan, and explain why each place fits. It returns only Qloo-grounded venue data, including affinity scores and per-interest contributions.