Bitgo Holdings Inc. (NYSE: BTGO) announced on Monday the launch of its Model Context Protocol (MCP) server, a gateway designed to connect its institutional cryptocurrency platform directly with AI-driven development environments. The tool aims to accelerate the creation of crypto solutions by enabling developers to query documentation using natural language, eliminating the need to manually search through technical guides.
How the MCP Server Works
The MCP server is built on the open standard introduced by Anthropic, providing a common framework for AI systems to access external data sources. Bitgo’s implementation links AI tools—including ChatGPT, Claude, Cursor, JetBrains IDEs, Visual Studio Code, and Windsurf—to its Developer Portal. Developers can ask questions like “how to create a wallet” or “how to access staking endpoints” and receive answers directly extracted from official Bitgo documentation. The system can also retrieve full pages, generate code snippets, and explain API functionality on demand.
Configuration is minimal: adding a single endpoint to an MCP-compatible client reduces what once required browsing multiple tabs to a matter of seconds. However, Bitgo emphasized that the current version is limited to documentation access and contextual support. It does not execute transactions, manage custody, or perform on-chain operations through AI agents. This boundary is intentional—the first iteration stays firmly on the side of “reading and assistance” rather than “action and transaction.”
CEO Vision and Industry Context
CEO Mike Belshe framed the launch as a first step toward broader automation. “AI is changing the way developers build, navigate technical systems, and interact with infrastructure,” Belshe said. “Developers can now treat Bitgo as agentic infrastructure—and this is just the first step toward making our platform fully accessible to the AI economy. There’s much more to come.”
The release comes amid a wider industry shift where crypto 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. Bitgo’s approach targets the institutional sector—custody, wallets, staking, and settlement—arguing that if AI agents are to manage large capital, they need infrastructure built for compliance and scalability.
Developer Impact and Availability
For developers, the MCP server reduces time spent searching documentation, allowing AI tools to provide accurate answers and code guidance instantly. Bitgo also noted that its Developer Portal already includes an embedded “Ask AI” feature on documentation pages, enabling users to query content without setting up external tools.
The MCP server is available immediately to existing Bitgo developers at no additional cost. Setup instructions and examples are published in the company’s developer docs. The tool integrates with widely used AI platforms and development environments, making it accessible to a broad audience.
Future Directions
While the current version focuses on read-only access, Belshe hinted at more capabilities ahead. The MCP standard itself, introduced by Anthropic, is gaining traction in both AI and crypto circles. Bitgo’s implementation uses a public endpoint linked to its documentation system, giving AI clients direct access to updated materials without relying on static training data—ensuring answers remain current.
As the industry watches, Bitgo’s move signals a shift toward AI-friendly infrastructure. Circle’s recent experiment with nanopayments for AI agents (see Circle’s nanopayment system) further underscores the trend. For now, Bitgo’s 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.