RugSense
Agent-native scored launch intelligence for Base blockchain, providing opportunity/risk scores and AVOID/WATCH/HOT decisions per fresh launch via x402 pay-per-call API. Enables trading/research agents to act directly on structured launch data.
README
RugSense
Agent-native scored launch intelligence for Base — sold per-call over x402 (USDC).
Not another raw "new pairs" feed (DexScreener already owns that, free). The wedge:
a single x402-payable call that returns, per fresh Base launch, a composite
opportunity/risk score + structured flags + an AVOID / WATCH / HOT decision
that a trading/research agent can act on directly — the gap between DexScreener
(raw, human-first) and GoPlus (security-only).
How it works
onchain DEX factory events (viem) ─┐
DexScreener enrich (liq/vol/age) ├─► scoring engine (deterministic, no LLM) ──► /api/launches/latest
honeypot.is (honeypot/tax/verified/proxy) safety + momentum → composite → AVOID/WATCH/HOT (x402 v2, USDC on Base)
holder concentration + LP burn/lock ─┘ + transparent checks[] + safetyConfidence
- 🟢 Live on Base mainnet, earning per-call. Discoverable on x402 Bazaar / Agentic.Market.
- Buyers: AI agents (via x402 + the MCP server) and humans (the landing page).
- Cost: ~$0 — free hosting + free data APIs; no LLM; payer covers gas (EIP-3009).
Run
npm install
npm run score:demo # scoring sanity check (no network)
npm test # deterministic scoring test suite
npx tsx scripts/verify-live.ts # live: discovery → enrich → score (needs network)
npm run daily # generate a daily "today's HOT / filtered rugs" post
npm run dev # http://localhost:3000 + /api/launches/latest
BUYER_PRIVATE_KEY=0x… npm run mcp # MCP server (get_base_launches tool)
Use it
- Endpoint:
GET /api/launches/latest?limit=20&tier=HOT&minSafety=60(x402 v2, $0.03 USDC/call). - Integration guide (curl / x402 client / MCP):
docs/INTEGRATE.md. - MCP server:
mcp/README.md.
Status
- [x] Onchain discovery + DexScreener enrichment + deterministic scoring (
src/lib/scoring.ts). - [x] Hardened safety (
src/lib/assess.ts): honeypot+tax+verified+proxy (honeypot.is), mint/ blacklist/pause+ownership (RPC), holder concentration + v2/v3 LP burn-lock. Transparentchecks[]+safetyConfidence. Security-audited (SECURITY.md). - [x] x402 v2 (
@x402/next+ paymentProxy middleware + BazaardeclareDiscoveryExtension). Real mainnet paid round-trip verified. - [x] Live on mainnet + indexed on x402 Bazaar / Agentic.Market.
- [x] MCP server (
mcp/), human storefront, daily content generator, test suite. - [ ] Custom domain (dedicated-domain quality signal); Farcaster mini-app (MiniKit) + auto-poster.
- [ ] Dedicated factory-event indexer (lower latency than the DexScreener bootstrap).
Orientation for a new session: CLAUDE.md. Plan/business: docs/.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.