AgentSignal
JSON →Collective intelligence for AI shopping agents â 23 MCP tools for buyer intelligence, seller analytics, price alerts, and trend tracking.
Install
npx agent-signal Tools · 23
- smart_shopping_session Start session + get category intelligence + similar session outcomes — all in one call
- evaluate_and_compare Log product evaluation + get product intelligence + deal verdict — all in one call
- get_product_intelligence Selection rate, rejection reasons, which competitors beat it and why
- get_category_recommendations Top picks, decision factors, common requirements, average budgets
- check_merchant_reliability Stock accuracy, selection rate, purchase outcomes by merchant
- get_similar_session_outcomes What agents with similar constraints ended up choosing
- detect_deal Price verdict against historical data — best_price_ever to above_average
- get_warnings Stock issues, high rejection rates, abandonment signals
- get_constraint_match Products that exactly match your constraints — skip the search
- get_competitive_landscape Category rank, head-to-head win rate, who beats you and why, price positioning
- get_rejection_analysis Why agents reject your product, weekly trends, what they chose instead
- get_category_demand What agents are searching for, unmet needs, budget distribution, market gaps
- get_merchant_scorecard Full merchant report — stock reliability, price competitiveness, selection rates by category
- get_budget_products Best products within a specific budget — ranked by agent selections, with merchant availability
- get_trending_products Products trending up or down — compares current vs previous period selection rates
- create_price_alert Set a price alert — triggers when agents spot the product at or below your target
- check_price_alerts Check which alerts have been triggered by recent agent activity
- log_shopping_session Shopping intent, constraints, budget, exclusions
- log_product_evaluation Product considered, match score, disposition + rejection reason
- log_comparison Products compared, dimensions, winner, deciding factor
- log_outcome Final result — purchased, recommended, abandoned, or deferred
- import_completed_session Bulk import a completed session retroactively
- get_session_summary Retrieve full session details
Environment variables
DATABASE_URL