When we started @TaironAI, there wasn’t really a “product idea.” We just wanted to understand how Model Context Protocol could connect different parts of crypto infra. So we built a directory of open MCP servers, a playground to test things. Each one was different: some for DeFi, some for chains, some for social data. They weren’t supposed to be connected, it was just a way to prototype and see what’s possible. At some point we realized: this playground was exactly what the market needed. A structured way to connect data, actions, and context across protocols. We started writing our own MCP servers from scratch. The goal was to standardize the codebase, one format, one style, one set of interfaces for every type of integration. Once that was done, we moved to a more systematic structure with three clear layers: 1️⃣ Chains: Base, Sonic, BSC, Plasma, Telos, Sei, Monad… and some non-EVMs like Phala, Algorand, Secret. 2️⃣ Liquidity protocols: Aerodrome, Aave, Uniswap, PancakeSwap, bridges, etc. 3️⃣ Analytics & data: DefiLlama, Codex, Chainlink, explorers, and other sources that feed the system. That’s the structure behind what we call the MCP Supergraph, a connected network of servers where data, liquidity, and computation meet. The Supergraph isn’t just about connecting chains, it’s about creating one layer where: - agents or devs can query data, - execute onchain actions, - and build automations across protocols without rewriting integrations every time. Each MCP server is like a puzzle piece, consistent format, open interface, verifiable output. The more pieces we add, the more powerful the network becomes. We’re focused on expanding EVM coverage first (Base, Sonic, Monad, etc.) while keeping other L1s moving in parallel. At the same time, we’re finalizing SDKs and internal tooling so new servers can be deployed faster and more consistently. Next step, bringing it all together into one Supergraph endpoint where agents, apps, and even robotics systems can interact directly with onchain data. Piece by piece, it’s coming together.