Provides merchant intelligence and shopping analytics for Amazon, including merchant reliability scoring, stock accuracy, price competitiveness, and selection rate analysis across categories.
Provides competitive intelligence and product analytics for Bose products, including rejection analysis, head-to-head comparisons with competitors like Sony, and market positioning insights.
Provides ready-to-run examples for CrewAI framework, enabling multi-agent shopping crews (researcher + shopper) to leverage collective shopping intelligence.
Provides REST API endpoints for merchant-facing analytics, including product insights, category trends, competitive analysis, and session management.
Hosts the MCP server repository with examples, documentation, and source code for the AgentSignal collective intelligence platform.
Provides ready-to-run examples for LangChain framework, enabling ReAct agents with LangGraph integration to access shopping intelligence through MCP tools.
Integrates with LangGraph for building ReAct agents that can leverage collective shopping intelligence through the MCP server's tools.
Provides package distribution and installation via npm, enabling easy deployment and usage of the AgentSignal MCP server.
Provides ready-to-run examples for OpenAI Agents SDK, enabling AI shopping agents with streamable HTTP capabilities to access collective intelligence.
Provides database backend for storing shopping session data, product intelligence, merchant analytics, and collective learning insights.
Provides hosting and deployment platform for the production MCP server, enabling remote access to shopping intelligence without local installation.
Provides competitive intelligence and product analytics for Sony products, including category ranking, head-to-head win rates, and market positioning insights.
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.
Remote — zero install, instant intelligence:
{
"mcpServers": {
"agent-signal": {
"url": "https://agent-signal-production.up.railway.app/mcp"
}
}
}Local via npx:
npx agent-signalClaude Desktop / Claude Code:
{
"mcpServers": {
"agent-signal": {
"command": "npx",
"args": ["agent-signal"]
}
}
}Related MCP server: Godalo
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
Tool | What it does |
| Start session + get category intelligence + similar session outcomes — all in one call |
| Log product evaluation + get product intelligence + deal verdict — all in one call |
Tool | What it tells you |
| Selection rate, rejection reasons, which competitors beat it and why |
| Top picks, decision factors, common requirements, average budgets |
| Stock accuracy, selection rate, purchase outcomes by merchant |
| What agents with similar constraints ended up choosing |
| Price verdict against historical data — best_price_ever to above_average |
| Stock issues, high rejection rates, abandonment signals |
| Products that exactly match your constraints — skip the search |
Tool | What it tells you |
| Category rank, head-to-head win rate, who beats you and why, price positioning |
| Why agents reject your product, weekly trends, what they chose instead |
| What agents are searching for, unmet needs, budget distribution, market gaps |
| Full merchant report — stock reliability, price competitiveness, selection rates by category |
Tool | What it tells you |
| Best products within a specific budget — ranked by agent selections, with merchant availability |
| Products trending up or down — compares current vs previous period selection rates |
| Set a price alert — triggers when agents spot the product at or below your target |
| Check which alerts have been triggered by recent agent activity |
Tool | What it captures |
| Shopping intent, constraints, budget, exclusions |
| Product considered, match score, disposition + rejection reason |
| Products compared, dimensions, winner, deciding factor |
| Final result — purchased, recommended, abandoned, or deferred |
| Bulk import a completed session retroactively |
| Retrieve full session details |
# 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.
# 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 instead 3x more
# 3. What do agents want in my category?
get_category_demand(category: "electronics/headphones")
# → Top demands: noise-cancelling (89%), wireless (82%), unmet need: "spatial audio"
# 4. How does my store perform?
get_merchant_scorecard(merchant_id: "amazon")
# → 34% selection rate, 2% out-of-stock, cheapest option 41% of the timeCategory | Sessions |
footwear/running | 150+ |
electronics/headphones | 140+ |
gaming/accessories | 130+ |
electronics/tablets | 130+ |
home/furniture/desks | 120+ |
fitness/wearables | 118+ |
electronics/phones | 115+ |
home/smart-home | 107+ |
kitchen/appliances | 105+ |
electronics/laptops | 98+ |
Ready-to-run examples in /examples:
Framework | File | Description |
LangChain | ReAct agent with LangGraph + MCP adapter | |
CrewAI | Two-agent crew (researcher + shopper) | |
AutoGen | AutoGen agent with MCP tools | |
OpenAI Agents | OpenAI Agents SDK with Streamable HTTP | |
Claude | Optimized system prompt for Claude Desktop/Code |
All examples connect to the hosted MCP endpoint — no setup beyond pip install required.
Merchant-facing analytics at https://agent-signal-production.up.railway.app/api:
Endpoint | Description |
| Product analytics — consideration rate, rejection reasons |
| Category trends — top factors, budgets, attributes |
| Competitive losses — what X loses to and why |
| Recent sessions (paginated) |
| Full session detail |
| Trigger insight computation |
| Health check |
git clone https://github.com/dan24ou-cpu/agent-signal.git
cd agent-signal
npm install
cp .env.example .env # set DATABASE_URL to your PostgreSQL
npm run migrate
npm run seed # optional: sample data
npm run dev # starts API + MCP server on port 3100MCP Server — Stdio transport (local) + Streamable HTTP (remote)
REST API — Express on the same port
Database — PostgreSQL (Neon-compatible)
23 MCP tools — 17 read (buyer + seller + discovery) + 6 write
MIT
This server cannot be installed
Product discovery for AI agents: ranked products and bundles from the open merchant web.
Agent-native product catalog for AI shopping agents. 296M+ products, 28 countries.
Verified, sourced, real-time intelligence layer for AI agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dan24ou-cpu/agent-signal'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
