Custody and infrastructure provider Bitgo Holdings Inc. (NYSE: BTGO) announced the launch of its Model Context Protocol (MCP) server on Monday, a tool designed to bridge AI-driven development environments with Bitgo's institutional crypto platform. The release positions Bitgo directly in the growing movement to make crypto infrastructure accessible to AI agents, not just humans clicking through dashboards.
Connecting AI to Crypto Documentation
The MCP server connects AI tools to Bitgo's Developer Portal, enabling natural language interaction with technical documentation. Developers can ask questions like “how to create a wallet” or “how to access staking endpoints” and receive answers extracted directly from official Bitgo docs. The system can also retrieve full pages, generate code snippets, and explain API functionality on demand.
The tool integrates with widely used AI platforms including ChatGPT, Claude, Cursor, JetBrains IDEs, Visual Studio Code, and Windsurf. Configuration requires adding a single endpoint to an MCP-compatible client, reducing what once took multiple browser tabs to mere seconds.
No Transaction Execution – A Deliberate Safety Measure
Bitgo emphasized that the MCP server is currently limited to documentation access and contextual support. It does not execute transactions, manage custody, or perform on-chain operations through AI agents. This limitation is crucial: while the industry has flirted with fully autonomous crypto agents, Bitgo keeps the first iteration firmly in “read and assist” territory rather than “act and transact.”
CEO Mike Belshe framed the launch as a first step toward broader automation. “AI is changing how developers build, navigate technical systems, and interact with infrastructure,” Belshe said. “Developers can now treat Bitgo as agent infrastructure—and this is just the first step in making our platform fully accessible to the AI economy. Much more is coming.”
MCP Standard and Industry Context
The MCP standard, introduced by Anthropic, is gaining traction in both AI and crypto circles. It provides a common framework for connecting AI systems to external data sources, reducing the need for custom integrations. Bitgo's implementation uses a public endpoint linked to its documentation system, giving AI clients access to up-to-date materials without relying on static training data. The company also noted its Developer Portal already includes a built-in “Ask AI” feature on documentation pages, allowing users to query content without configuring external tools.
The MCP server is available immediately to existing Bitgo developers at no extra cost. Setup instructions and examples are published in the company's developer documentation. The launch comes amid a broader industry shift where platforms are racing to make their services AI-native. Competitors and adjacent projects are experimenting with similar MCP-based systems, particularly for trading and on-chain interactions.
Institutional Focus and Future Steps
Bitgo's approach targets the institutional sector—custody, wallets, staking, and settlement. The thinking goes: if AI agents are to manage large capital, they need access to infrastructure built for compliance and scalability. For now, the MCP server handles the basics: faster development, cleaner integrations, and fewer excuses for developers to get lost in documentation. The more complex parts of automation appear to be waiting in the wings.
In a related context, the same report also highlighted Circle's bet on nanopayments for AI agents and streaming commerce, allowing ultra-low-value USDC transfers designed for machine-to-machine payments. These developments collectively underscore the industry's pivot toward AI-native infrastructure—and Bitgo's MCP server marks a significant milestone in that journey.