🔍 Disvr

Spend Intelligence for AI Agents — the "Yelp for the Agent Economy"

Why Disvr · Quick Start · API · Architecture · Live Demo · 中文文档

Why Disvr?

The AI Agent ecosystem is exploding. Payment protocols (Stripe MPP, OpenAI ACP, x402) solve how to pay. Directories (Smithery, Composio) solve what exists.

But nobody solves the most critical question: which tool is actually worth using?

🤖 "Translate a Chinese legal contract to Thai" → 50 translation services on Smithery. Which one has the best cost/quality ratio?

🤖 "Scrape product prices from e-commerce sites" → 30 scraping tools. Which one has the highest success rate and lowest latency?

🤖 "Generate a product image" → 20 image generation services. Which one is cheapest while still being good enough?

Right now, agents pick blindly. Wrong picks mean wasted money, wasted time, and failed tasks.

Disvr fixes this.

Instead of returning a list, Disvr returns a ranked recommendation — based on a 4-dimensional value score:

Your agent stops guessing and starts choosing the best tool for the job.

✅ Before You Start

Quick Start

Option 1: MCP Server (Recommended)

Add one line to your .mcp.json:

{
  "mcpServers": {
    "disvr": {
      "type": "url",
      "url": "https://api.disvr.top/mcp"
    }
  }
}

Restart Claude Code / Cursor — your agent now has the discover_services tool.

Try telling your agent:

• "Find the best tool to translate Chinese legal documents to Thai"
• "Recommend the cheapest web scraping service with high success rate"
• "Which image generation API has the best price/quality ratio?"

Option 2: REST API

curl -X POST https://api.disvr.top/discover \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"need": "translate Chinese legal contract to Thai"}'

Returns Top 3 recommendations ranked by value_score:

{
  "recommendations": [
    {
      "service": "deepl-mcp-server",
      "platform": "smithery",
      "match_confidence": 0.92,
      "reputation": 4.2,
      "price_usd": 0.002,
      "reason": "Best cost/quality ratio for legal document translation"
    }
  ]
}

Live Demo

API Reference

POST /discover — Service Discovery

Describe what your agent needs, get back Top 3 ranked recommendations.

POST https://api.disvr.top/discover
Authorization: Bearer <api-key>
Content-Type: application/json

{
  "need": "scrape product prices from e-commerce websites",
  "max_price_per_call": 0.01,
  "max_latency_ms": 5000,
  "min_reputation": 3.0
}

POST /report — Feedback Loop

Report call results after using a tool — closes the feedback loop and improves rankings.

POST https://api.disvr.top/report
Authorization: Bearer <api-key>
Content-Type: application/json

{
  "service_id": "deepl-mcp-server",
  "query_id": "q_abc123",
  "success": true,
  "latency_ms": 1200,
  "cost_usd": 0.002
}

GET /health — Health Check

curl https://api.disvr.top/health
# {"status": "ok", "services_indexed": 330}

MCP Tools

Tools exposed via the MCP Server:

SDK

TypeScript/JavaScript SDK with full type safety:

npm install @sylar_yan/disvr

import { Disvr } from "@sylar_yan/disvr";

const client = new Disvr("dsvr_your_api_key");

const result = await client.discover({
  need: "translate Chinese legal contract to Thai",
  max_latency_ms: 3000,
  min_reputation: 3.5,
});

console.log(result.recommendations);

• npm
• GitHub

Architecture

Agent Query ("I need X")
       │
       ▼
┌─────────────────────────────────────────┐
│  Disvr API (Cloudflare Workers + Hono)  │
├─────────────────────────────────────────┤
│                                         │
│  ┌──────────┐    ┌──────────────────┐   │
│  │ Embed    │───▶│ CF Vectorize     │   │
│  │ (OpenAI) │    │ (1536-dim cosine)│   │
│  └──────────┘    └────────┬─────────┘   │
│                           │             │
│         ┌─────── 50 candidates ──────┐  │
│         ▼                            │  │
│  ┌──────────────┐   ┌────────────┐   │  │
│  │ D1 Database  │   │ FTS5       │   │  │
│  │ (services,   │   │ (fallback) │   │  │
│  │  call_reports)│   └────────────┘   │  │
│  └──────┬───────┘                    │  │
│         │                            │  │
│         ▼                            │  │
│  ┌──────────────────────────────┐    │  │
│  │ 4-Dim Value Ranking          │    │  │
│  │ semantic × 0.30              │    │  │
│  │ quality  × 0.25              │    │  │
│  │ cost_eff × 0.25              │    │  │
│  │ reliable × 0.20              │    │  │
│  └──────────┬───────────────────┘    │  │
│             ▼                        │  │
│        Top 3 Recommendations         │  │
│                                      │  │
├──────────────────────────────────────┤  │
│  MCP Server (Streamable HTTP)        │  │
│  via CF Agents SDK + Durable Objects │  │
└──────────────────────────────────────┘  │
                                          │
       ┌──────────────────────────────────┘
       ▼
  ┌─────────────┐
  │ Cron Trigger │  ← Hourly: crawl (Smithery + GitHub + MCP Registry)
  │ (4-phase)    │     → enrich GitHub Stars → health checks
  └─────────────┘     → aggregate daily stats
       │
  ┌────▼────────────┐
  │ POST /report    │  ← Agent feedback
  │ refreshStats()  │     success_rate, latency → ranking improvement
  └─────────────────┘

Tech Stack

Project Structure

disvr/
├── wrangler.toml           # CF Workers config
├── schema.sql              # D1 database schema
├── src/
│   ├── index.ts            # Hono entry + REST routes
│   ├── discover.ts         # Core: semantic search + 4-dim ranking
│   ├── db.ts               # D1 CRUD + feedback stats
│   ├── crawl.ts            # Multi-source crawlers + embedAndIndex
│   ├── mcp.ts              # MCP Server (Streamable HTTP)
│   ├── types.ts            # TypeScript type definitions
│   ├── landing.ts          # Landing page HTML
│   └── pages/
│       ├── registry.ts     # Provider Registry page
│       ├── explorer.ts     # Agent Query Explorer page
│       └── analytics.ts    # Analytics Dashboard page
├── test/
│   ├── types.test.ts       # Type conversion tests
│   ├── discover.test.ts    # Matching engine tests
│   ├── db.test.ts          # D1 operations tests
│   ├── api.test.ts         # REST API integration tests
│   └── crawl.test.ts       # Crawler tests
└── .mcp.json               # MCP config example

Local Development

# Prerequisites: Node.js 22+
nvm use 22

# Install dependencies
npm install

# Local dev server
npx wrangler dev

# Run tests
npx vitest run

# Deploy
npx wrangler deploy

Environment Variables

# Set OpenAI API Key (for embeddings)
wrangler secret put OPENAI_API_KEY

Database Setup

# Create D1 database
wrangler d1 create disvr-db

# Run schema
wrangler d1 execute disvr-db --file=./schema.sql

# Create Vectorize index
wrangler vectorize create disvr-mcp-index --dimensions=1536 --metric=cosine

Design Philosophy

Spend Intelligence, Not Just Search

Disvr is not a directory. It's not a marketplace. It's a decision layer.

Traditional directories return a list and let you pick. Disvr returns a recommendation and tells you:

• Why this tool is worth using
• How its cost/quality ratio compares
• What makes it better than alternatives

Closed-Loop Feedback is the Moat

Every time an agent reports a call result (success/failure, latency, cost), it feeds back into the ranking algorithm. More usage → smarter recommendations. This isn't a static database — it's a living intelligence system.

Dual-Path Search Guarantees Recall

• Primary: OpenAI embedding → CF Vectorize vector search (semantic matching)
• Fallback: FTS5 full-text search (OR + prefix wildcards)
• Automatically degrades when embedding fails or vector search returns empty — always returns results

Roadmap

• Core API (discover + report + health)
• MCP Server (Streamable HTTP)
• Smithery crawler (330+ services)
• GitHub awesome-mcp crawler + Stars enrichment
• MCP Official Registry crawler (1000+ services)
• Landing page + 4 frontend pages
• Custom domains (www.disvr.top + api.disvr.top)
• npm SDK (@sylar_yan/disvr)
• 90 unit tests (types, discover, db, api, crawl)
• Request logging + Analytics API
• Daily stats cron aggregation
• Health checks + multi-signal reputation scoring
• User registration + API key management UI
• Agent integration verification (MCP real-world testing)
• Cost tracking dashboard
• Payment protocol integration (Stripe MPP / x402)

Contributing

PRs and Issues are welcome!

• 🐛 Bug reports → GitHub Issues
• 💡 Feature requests → GitHub Issues
• 🔧 Code contributions → Fork & PR

Acknowledgments

• Cloudflare Workers — Global edge compute
• Hono — Lightweight web framework
• Smithery — MCP service registry
• OpenAI — text-embedding-3-small
• CF Agents SDK — MCP Server implementation

License

MIT

Stop guessing. Start discovering.
www.disvr.top · MCP Server · API Status