Moltllama
@moltllama
Real-time DeFi data for AI agents. 8 MCP endpoints covering protocol TVL, yields, prices, DEX volumes, fees, contracts, and chain analytics — powered by DeFiLlama. Supports Base and Ethereum.
Overview
What is Moltllama?
Moltllama aggregates DeFi protocol data from DeFiLlama into an MCP API, REST API, and web dashboard for AI agents and developers. It provides contract interfaces, yields, prices, and DEX volumes across Ethereum and Base chains.
How to use Moltllama?
Install dependencies with npm install, copy .env.example to .env.local, and run npm run dev to start at localhost:3000. For AI agent integration, add the MCP URL https://moltllama.com/api/mcp to your agent’s MCP configuration. No environment variables are required for development; production may use Upstash Redis and optional API keys.
Key features of Moltllama
- MCP API for AI agents to call DeFi tools
- REST API at
/api/mcp/*endpoints - Browser dashboard for protocols, yields, and DEX volumes
- Supports Ethereum and Base chains
- Tracks yields, prices, fees, and contract interfaces
- Integrates with Aave V3, Uniswap V3, Compound V3, and more
Use cases of Moltllama
- AI agents executing DeFi tasks like checking yields or fetching prices
- Developers querying protocol data via REST for custom dashboards
- Analysts browsing current TVL, fees, and DEX volumes interactively
FAQ from Moltllama
What protocols and chains does Moltllama support?
Moltllama supports Ethereum and Base chains, with protocols including Aave V3, Uniswap V3, Compound V3, Aerodrome, Morpho, and Moonwell.
Do I need an API key to use Moltllama?
No API key is required for development. Optional keys (DEFILLAMA_API_KEY, COINGECKO_API_KEY) can be set in .env.local to access Pro-tier data or fallback providers.
Where does Moltllama’s data come from and how is it cached?
Data is aggregated from DeFiLlama. In development, caching uses an in-memory LRU; in production, Upstash Redis is used with UPSTASH_REDIS_REST_URL and UPSTASH_REDIS_REST_TOKEN.
How do I add Moltllama to an AI agent?
Add the following to your agent’s MCP server configuration: "moltllama": { "url": "https://moltllama.com/api/mcp" }. The agent can then call endpoints like /api/mcp/protocols and /api/mcp/yields.
Can I use Moltllama in production without Redis?
Yes, the README notes that caching falls back to in-memory LRU when no Redis environment variables are set, but Upstash Redis is recommended for production.
