Sylex Search — Universal Search for AI Agents

Sylex Search — A search engine that lets AI agents discover, evaluate, and compare products, services, and businesses across every category through MCP.

Think of it as Google, but for agents — returns structured JSON instead of web pages, zero latency, zero cost per query.

Why this exists

McKinsey projects $1 trillion in sales will flow through AI agents. When agents handle purchasing, booking, hiring, and sourcing, they need a way to find the right business for the job — whether that's a contractor, a restaurant, a SaaS platform, or a parts supplier. If a business isn't in the index, it's invisible to agents.

Sylex Search is the discovery layer for agent commerce.

What's in the index

11,000+ entries and growing. The index currently includes:

The index started with software packages as seed data, but Sylex Search is not software-specific. The schema and tools support any product, service, or business. More categories are being added.

Quick start

Add to your MCP client config:

{
  "mcpServers": {
    "sylex-search": {
      "url": "https://mcp-server-production-38c9.up.railway.app/sse"
    }
  }
}

Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client.

Tools

Self-service registration

Any business or product can be listed in Sylex Search — no human portal needed. An agent can register a listing, verify ownership, and manage it entirely through MCP tool calls.

Example queries

• "react state management" → zustand, redux, mobx, jotai
• "python web framework" → Django, Flask, FastAPI, Sanic
• "project management" → Notion, Jira, Asana, Linear
• "database" → PostgreSQL, MongoDB, Redis, SurrealDB

Architecture

• Zero LLM calls at query time — all search is deterministic (Postgres FTS + custom ranking)
• Millisecond responses — no API calls, no model inference
• $0 per query — no token costs
• Structured JSON — agents parse directly, no scraping needed
• Agents-first — no dashboards, no accounts, no human UI

Self-hosting

pip install -r requirements.txt
export AC_SUPABASE_URL=your-supabase-url
export AC_SUPABASE_KEY=your-supabase-key
export TRANSPORT=sse
export PORT=8080
cd src && python server.py

License

MIT