The Graph Integrates Mode Network and Expands Blockchain Support

The Graph Network now enables users to query lending rates across 40+ DeFi protocols simultaneously using natural language through its Graph Lending MCP integration. **How it works:** - Single query like "Where can I find the best stablecoin lending rates?" searches multiple protocols at once - Returns structured, comparable results across dozens of chains - Powered by standardized Subgraph schemas that solve DeFi's data fragmentation problem **The technical breakthrough:** Messari's standardized Subgraphs eliminated the need for 40 different schemas and custom adapters. Combined with MCP (Model Context Protocol), this creates AI-accessible DeFi data that works in tools like Claude. Previously, comparing rates meant manually checking each protocol. Now standardized schemas make cross-protocol queries possible through a unified interface. [Learn more about The Graph](https://thegraph.com)

**Three foundational web3 standards are now working together in production on Base:** - **ERC-8004** - handles identity - **x402** - enables payments - **Subgraphs** - manages data access This marks a significant milestone as these complementary protocols operate simultaneously in a live environment. The integration demonstrates practical interoperability between identity, payment, and data infrastructure layers. **Background:** x402 recently went live on The Graph's Subgraph Gateways, allowing compatible clients to pay per query in USDC for accessing blockchain data across multiple networks. The payment standard now works alongside traditional API-key access. The combination of these three standards creates a complete stack for decentralized applications on Base.

**PaySponge** has built a financial platform where every new agent automatically connects to **The Graph** without additional integration. - Agents like **Michaelgent** and **Clarabotagent** aren't standalone scripts—they're part of a unified infrastructure designed for the agent economy - Each new agent inherits the same routing path, eliminating setup friction - This represents a shift from hobbyist experimentation to platform-level growth The approach suggests a different scaling model: rather than individual agents building custom integrations, they plug into shared financial rails from day one.

**AI agents operate at machine speed**, making thousands of decisions per minute in the crypto economy. Unlike humans who browse block explorers, these agents require **structured, normalized, and queryable blockchain data** to function effectively. - Agents assessing DeFi risk cannot work with raw transaction logs - They need data formatted for rapid querying and decision-making - The infrastructure enabling this agent economy operates behind the scenes This represents a fundamental shift in how blockchain data must be organized and accessed. As AI agents become more prevalent in web3, the demand for **properly structured data infrastructure** will intensify dramatically. The agent economy isn't about human-readable interfaces—it's about machine-optimized data pipelines that can support thousands of automated decisions every minute.

**Agent0 Subgraphs are now operational across five major blockchain networks** - Base, BNB Chain, Ethereum, Monad, and Polygon - using a single GraphQL schema. **Key features:** - Real-time indexing of every ERC-8004 agent across all chains - No code rewrites needed when switching between networks - Already processed over 1 million queries - Accessible via [Graph Explorer](https://thegraph.com/explorer?search=agent0) **What this enables:** - Developers can query agent data with a single GraphQL request instead of scanning thousands of blocks - AI agents can discover, hire, and interact with each other using structured blockchain data - Machine-scale data access for agents that operate continuously The infrastructure indexes agent identities, capabilities, reputation, and validation data in milliseconds. Developers building ERC-8004 agents can now access comprehensive onchain data without building custom indexers.