What is an MCP Server?

An MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. In the context of Spinnaker, it provides a standardized interface for AI models to access information about deployments, pipelines, and applications.

How does the MCP Server integrate with Spinnaker?

The MCP Server for Spinnaker integrates directly with your Spinnaker Gate service. It uses the Gate API to retrieve information about your applications, pipelines, and deployments. The server then provides this information to AI models in a standardized format.

What AI models can I use with the MCP Server?

The MCP Server is designed to work with any AI model that supports the Model Context Protocol (MCP). This includes models like Anthropic’s Claude, as well as other LLMs and AI agents.

What kind of data can AI models access through the MCP Server?

AI models can access a wide range of data, including:

• A list of monitored Spinnaker applications and their current state
• Pipeline status for each application
• Current deployments across monitored environments
• Recent pipeline executions

How often does the MCP Server refresh its context?

By default, the MCP Server refreshes its context every 30 seconds. This ensures that AI models always have access to the most up-to-date information. The refresh interval can be configured using the REFRESH_INTERVAL environment variable.

Can I use the MCP Server with multiple Spinnaker instances?

Yes, you can use the MCP Server with multiple Spinnaker instances. Simply configure the server with the appropriate Gate URL for each instance.

What are the benefits of using the MCP Server?

Using the MCP Server offers numerous benefits, including:

• Increased efficiency through AI-driven automation
• Improved reliability through proactive issue detection and remediation
• Continuous process optimization through AI-powered learning and adaptation
• Faster root cause analysis and recovery
• Enhanced security through real-time vulnerability monitoring
• Cost optimization through intelligent resource management

Is the MCP Server open source?

Yes, the MCP Server is licensed under the MIT License and is open source. This allows you to contribute to the development and customize the server to your specific needs.

How can I contribute to the development of the MCP Server?

You can contribute to the development of the MCP Server by:

• Forking the repository on GitHub
• Making changes and submitting pull requests
• Reporting bugs and suggesting new features
• Writing documentation and tutorials