vertex-ai-mcp-server
Vertex AI MCP Server is a platform designed to facilitate interaction with Google Cloud's Vertex AI Gemini models. It offers a suite of tools for coding assistance and query answering, aiming to enhance development productivity with configurable and responsive AI capabilities.
What is the default behavior of the Vertex AI MCP Server?
The server uses a streaming API by default for enhanced responsiveness and includes basic retry logic to handle transient API errors.
How can I configure the server settings?
Server settings such as model ID, temperature, streaming behavior, and retry settings can be configured via environment variables.
What are the prerequisites for using the Vertex AI MCP Server?
You need Node.js (v18+), Bun, a Google Cloud Project with Billing enabled, and the Vertex AI API enabled in the GCP project.
Can I use the server with different AI providers?
Yes, you can set the AI_PROVIDER environment variable to either 'vertex' or 'gemini' depending on your preference.
Is there a way to run the server without cloning the repository?
Yes, you can use NPX to automatically download and run the server package from the npm registry.