MoltLlama
Real-time DeFi data for AI agents. Provides yields, TVL, prices, DEX volumes, fees, and contract data via 8 MCP endpoints, powered by DeFiLlama.
README
MoltLlama
DeFi data and contract interfaces for AI agents that execute real tasks.
Live at moltllama.com
What it does
MoltLlama aggregates DeFi protocol data from DeFiLlama into three surfaces:
- MCP API — Machine Context Protocol endpoints for AI agents to discover and call DeFi tools (protocols, yields, prices, DEX volumes, fees, contracts)
- REST API — JSON endpoints at
/api/mcp/*for any HTTP consumer - Dashboard — Web UI for browsing protocols, yields, DEX volumes, and contract interfaces
Supported chains: Ethereum, Base. Protocols include Aave V3, Uniswap V3, Compound V3, Aerodrome, Morpho, and Moonwell.
Quick start
npm install
cp .env.example .env.local
npm run dev
The app runs at localhost:3000. No environment variables are required for development — caching falls back to in-memory LRU.
MCP integration
Add to your AI agent's MCP config:
{
"mcpServers": {
"moltllama": {
"url": "https://moltllama.com/api/mcp"
}
}
}
API endpoints
| Endpoint | Description |
|---|---|
GET /api/mcp/protocols |
List all tracked protocols with TVL |
GET /api/mcp/protocols/[slug] |
Protocol detail (TVL, fees, revenue) |
GET /api/mcp/prices |
Current token prices |
GET /api/mcp/chains/[chain] |
Chain TVL and stats |
GET /api/mcp/yields |
Yield opportunities across protocols |
GET /api/mcp/dexs |
DEX trading volumes |
GET /api/mcp/fees |
Protocol fee data |
GET /api/mcp/contracts |
Contract addresses, ABIs, and function signatures |
Environment variables
| Variable | Required | Description |
|---|---|---|
UPSTASH_REDIS_REST_URL |
Production | Redis cache URL |
UPSTASH_REDIS_REST_TOKEN |
Production | Redis cache token |
DEFILLAMA_API_KEY |
No | DeFiLlama Pro API key |
COINGECKO_API_KEY |
No | CoinGecko Pro API key (fallback provider) |
BASE_RPC_URL |
No | Base chain RPC endpoint |
ETHEREUM_RPC_URL |
No | Ethereum RPC endpoint |
Tech stack
Next.js 14 (App Router) · TypeScript · Tailwind CSS · Recharts · Radix UI · SWR · Zod · Upstash Redis
License
All rights reserved.
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.