1inch expands its Model Context Protocol to allow AI agents to execute swaps and manage onchain portfolios in real time.
1inch Business announced the expansion of its Model Context Protocol (MCP) on March 30, 2026, to enable autonomous artificial intelligence (AI) agents to access decentralized finance infrastructure directly. The integration allows developers to build goal-oriented workflows where agents plan and execute swaps across the 1inch network using the Swap Application Programming Interface (API).
This update provides rapid access to a suite of 15 APIs, including Portfolio and Gas Price tools, reducing integration time from days to minutes. Developers maintain jurisdiction over automated strategies by setting strict rules for slippage thresholds, supported token pairs, and transaction signing methods to ensure secure execution.
“Agents, not humans, will be executing the majority of swaps by 2030,” said Sergej Kunz, 1inch co-founder. “However, the agent economy cannot eliminate market competition. Trading outcomes are still defined by data and execution quality. Poorly informed agents will underperform skilled humans. That is why choosing the infrastructure around the agent is as important as the strategy.”
🧭 FAQs
• What is the 1inch Model Context Protocol for developers? It provides AI agents direct access to infrastructure for executing onchain swaps and data analysis.
• Which AI development tools support the 1inch MCP integration? The protocol is compatible with over 10 local tools including Cursor, VS Code, and Gemini.
• How many APIs are available through this 1inch Business update? Developers can integrate 15 different APIs for comprehensive data access and automated trading execution.
• Does the 1inch MCP execute transactions on a custodial basis? The server provides non-custodial infrastructure and does not execute transactions on behalf of any party.
免责声明：本文章仅代表作者个人观点，不代表本平台的立场和观点。本文章仅供信息分享，不构成对任何人的任何投资建议。用户与作者之间的任何争议，与本平台无关。如网页中刊载的文章或图片涉及侵权，请提供相关的权利证明和身份证明发送邮件到support@aicoin.com，本平台相关工作人员将会进行核查。
