README.md
The collective intelligence layer for AI shopping agents.
AgentSignal
The collective intelligence layer for AI shopping agents.
Every agent that connects makes every other agent smarter. 1,200+ shopping sessions, 95 products, 50 merchants, 10 categories — and growing.
Why this exists: When AI agents shop for users, each agent starts from zero. AgentSignal pools decision signals across all agents so every session benefits from what every other agent has already learned — selection rates, rejection patterns, price intelligence, merchant reliability, and proven constraint matches.
Quick Start (30 seconds)
Remote — zero install, instant intelligence:
{
"mcpServers": {
"agent-signal": {
"url": "https://agent-signal-production.up.railway.app/mcp"
}
}
}
Local via npx:
npx agent-signal
Claude Desktop / Claude Code:
{
"mcpServers": {
"agent-signal": {
"command": "npx",
"args": ["agent-signal"]
}
}
}
One Call to Start Shopping Smarter
The smart_shopping_session tool logs your session AND returns all available intelligence in a single call:
smart_shopping_session({
raw_query: "lightweight running shoes with good cushioning",
category: "footwear/running",
budget_max: 200,
constraints: ["lightweight", "cushioned"]
})
Returns:
- Your session ID for subsequent logging
- Top picks from other agents in that category
- What constraints and factors mattered most
- How similar sessions ended (purchased vs abandoned)
- Network-wide stats
19 MCP Tools
Smart Combo Tools (recommended)
| Tool | What it does |
|---|---|
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 |
Buyer Intelligence — Shop Smarter
| Tool | What it tells you |
|---|---|
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 |
Seller Intelligence — Understand Your Market
| Tool | What it tells you |
|---|---|
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 |
Write Tools — Contribute Back
| Tool | What it captures |
|---|---|
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 |
Example: Full Agent Workflow
# 1. Start smart — one call gets you session ID + intelligence
smart_shopping_session(category: "electronics/headphones", constraints: ["noise-cancelling", "wireless"], budget_max: 400)
# 2. Evaluate products — get intel as you log
evaluate_and_compare(session_id: "...", product_id: "sony-wh1000xm5", price_at_time: 349, disposition: "selected")
evaluate_and_compare(session_id: "...", product_id: "bose-qc45", price_at_time: 279, disposition: "rejected", rejection_reason: "inferior ANC")
# 3. Compare and close
log_comparison(products_compared: ["sony-wh1000xm5", "bose-qc45"], winner: "sony-wh1000xm5", deciding_factor: "noise cancellation quality")
log_outcome(session_id: "...", outcome_type: "purchased", product_chosen_id: "sony-wh1000xm5")
Every step feeds the network. The next agent shopping for headphones benefits from your data.
Example: Seller Intelligence Workflow
# 1. How is my product performing vs competitors?
get_competitive_landscape(product_id: "sony-wh1000xm5")
# → Category rank #1, 68% head-to-head win rate, beats bose-qc45 on ANC quality
# 2. Why are agents rejecting my product?
get_rejection_analysis(product_id: "bose-qc45")
# → 45% rejected for "inferior ANC", agents chose sony-wh1000xm5
Tools (19)
smart_shopping_sessionStart session, get category intelligence, and similar session outcomes in one call.evaluate_and_compareLog product evaluation, get product intelligence, and receive a deal verdict.get_product_intelligenceRetrieve selection rate, rejection reasons, and competitor analysis for a product.get_category_recommendationsGet top picks, decision factors, common requirements, and average budgets for a category.check_merchant_reliabilityCheck stock accuracy, selection rate, and purchase outcomes by merchant.get_similar_session_outcomesSee what agents with similar constraints ended up choosing.detect_dealGet a price verdict against historical data.get_warningsCheck for stock issues, high rejection rates, or abandonment signals.get_constraint_matchFind products that exactly match specific constraints.get_competitive_landscapeAnalyze category rank, win rates, and price positioning.get_rejection_analysisUnderstand why agents reject a product and view weekly trends.get_category_demandIdentify what agents are searching for, unmet needs, and market gaps.get_merchant_scorecardGet a full merchant report on reliability and competitiveness.log_shopping_sessionLog shopping intent, constraints, budget, and exclusions.log_product_evaluationLog product consideration, match score, and disposition.log_comparisonLog products compared, dimensions, winner, and deciding factor.log_outcomeLog the final result of a shopping session.import_completed_sessionBulk import a completed session retroactively.get_session_summaryRetrieve full details of a shopping session.Configuration
claude_desktop_config.json
{"mcpServers": {"agent-signal": {"command": "npx", "args": ["agent-signal"]}}}Try it
→Start a shopping session for noise-cancelling wireless headphones under $400 and tell me what other agents recommend.
→Analyze why the Bose QC45 headphones are being rejected by other shoppers compared to the Sony WH-1000XM5.
→Check if the current price of $349 for the Sony WH-1000XM5 is considered a good deal based on historical data.
→What are the most common decision factors for users buying running shoes with cushioning?