Vertex AI
Implementation of Model Context Protocol (MCP) server that provides tools for accessing Google Cloud's Vertex AI Gemini models, supporting features like web search grounding and direct knowledge answering for coding assistance and general queries.
What is Vertex AI?
Vertex AI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to implementation of model context protocol (mcp) server that provides tools for accessing google cloud's vertex ai gemini models, supporting features like web search grounding and direct knowledge answe...
Implementation of Model Context Protocol (MCP) server that provides tools for accessing Google Cloud's Vertex AI Gemini models, supporting features like web search grounding and direct knowledge answering for coding assistance and general queries.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Implementation of Model Context Protocol (MCP) server that p
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx vertex-ai-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Vertex AI
Vertex AI MCP Server gives AI clients like Claude access to Google Cloud's Vertex AI and Gemini models as a secondary AI provider, enabling web-search-grounded answers, direct knowledge queries, code analysis, technology comparisons, and documentation generation through a unified set of tools. It supports both Google Cloud Vertex AI (authenticated via service accounts or Application Default Credentials) and the direct Gemini API, making it flexible for both enterprise GCP users and individual developers. Developers use it to run tasks that benefit from a different model's perspective or Google's real-time web search grounding, directly from Claude conversations.
Prerequisites
- Node.js 18 or higher and Bun runtime installed
- A Google Cloud project with Vertex AI API enabled and billing active, OR a Gemini API key from Google AI Studio
- Google Application Default Credentials configured (run `gcloud auth application-default login`) when using Vertex AI
- An MCP-compatible client such as Claude Desktop or Claude Code
Clone and build the server
Clone the repository and install dependencies using Bun.
git clone https://github.com/shariqriazz/vertex-ai-mcp-server.git
cd vertex-ai-mcp-server
bun install
bun run buildConfigure Google Cloud credentials
If using Vertex AI, set up Application Default Credentials. If using the Gemini API directly, you only need your GEMINI_API_KEY.
# For Vertex AI:
gcloud auth application-default login
# For Gemini API: set GEMINI_API_KEY in your environmentSet required environment variables
Set AI_PROVIDER to either 'vertex' or 'gemini', plus the corresponding project ID or API key.
# Vertex AI:
export AI_PROVIDER=vertex
export GOOGLE_CLOUD_PROJECT=your-gcp-project-id
export GOOGLE_CLOUD_LOCATION=us-central1
# Gemini API:
export AI_PROVIDER=gemini
export GEMINI_API_KEY=your_gemini_api_keyTest the server
Run the server to confirm it starts without authentication errors.
bunx vertex-ai-mcp-serverConfigure your MCP client
Add the server to your MCP client's configuration with the required environment variables set in the env block.
Vertex AI Examples
Client configuration
Claude Desktop configuration for the Vertex AI MCP server using the Gemini API provider.
{
"mcpServers": {
"vertex-ai": {
"command": "bunx",
"args": ["vertex-ai-mcp-server"],
"env": {
"AI_PROVIDER": "gemini",
"GEMINI_API_KEY": "your_gemini_api_key",
"GEMINI_MODEL_ID": "gemini-2.5-pro-exp-03-25",
"AI_TEMPERATURE": "0.0",
"AI_MAX_OUTPUT_TOKENS": "65536"
}
}
}
}Prompts to try
Example prompts leveraging Vertex AI tools for web-grounded answers, code analysis, and documentation.
- "Use Vertex AI to search the web and answer: what are the latest breaking changes in React 19?"
- "Ask Gemini to compare the performance characteristics of PostgreSQL vs. CockroachDB for distributed workloads"
- "Analyze this code file using Vertex AI and compare it against the official documentation for best practices"
- "Generate API documentation for this TypeScript module using the Vertex AI documentation tool"
- "Use Vertex AI to scan this package.json for dependency vulnerabilities"Troubleshooting Vertex AI
Authentication fails with 'Application Default Credentials not found'
Run `gcloud auth application-default login` to create ADC credentials, or set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of your service account JSON key file.
Vertex AI API returns 403 permission denied
Ensure the Vertex AI API is enabled in your Google Cloud project at console.cloud.google.com/apis, and that your authenticated account has the 'Vertex AI User' IAM role on the project.
bunx command not found
Install Bun from https://bun.sh using `curl -fsSL https://bun.sh/install | bash`. After installation, restart your terminal to ensure bunx is on your PATH.
Frequently Asked Questions about Vertex AI
What is Vertex AI?
Vertex AI is a Model Context Protocol (MCP) server that implementation of model context protocol (mcp) server that provides tools for accessing google cloud's vertex ai gemini models, supporting features like web search grounding and direct knowledge answering for coding assistance and general queries. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Vertex AI?
Follow the installation instructions on the Vertex AI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Vertex AI?
Vertex AI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Vertex AI free to use?
Yes, Vertex AI is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Vertex AI Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Vertex AI? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Vertex AI in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Vertex AI?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.