{"slug": "build-agents-even-faster-with-gemini-enterprise-agent-platforms-fully-managed", "title": "Build agents even faster with Gemini Enterprise Agent Platform’s fully-managed, remote MCP server", "summary": "Google announced the Gemini Enterprise Agent Platform's fully-managed, remote MCP server, enabling external AI agents to securely access Google Cloud resources like Model Garden models, prompt templates, and Notebooks via a standardized interface. The server, automatically enabled with the Gemini Enterprise Agent Platform API, allows developers to integrate external tools such as Antigravity CLI or Claude Code without leaving their IDE, balancing speed with governance.", "body_md": "A couple of months ago, we announced that [over 50 Google-managed MCP servers](https://cloud.google.com/blog/products/ai-machine-learning/google-managed-mcp-servers-are-available-for-everyone?e=48754805) are available.\n\nToday, we’ll dive into how to use the [ Gemini Enterprise Agent Platform remote MCP server](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/use-agent-platform-mcp) to securely connect your external AI agents to the resources inside your Google Cloud environment.\n\nThink of the Agent Platform MCP server as a bridge between your favorite external development tools and your Google Cloud architecture.\n\nIf you are building an agent in Antigravity CLI or Claude Code, for example, the Agent Platform MCP server allows that agent to securely interact with your Agent Platform resources. That way, your agent can now easily call [models from Model Garden](https://console.cloud.google.com/agent-platform/model-garden), pull down shared [prompt templates](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/prompts/prompt-templates), or even manage [Notebooks](https://docs.cloud.google.com/gemini-enterprise-agent-platform/notebooks/overview) directly within your project – all without ever leaving the IDE.\n\nThe speed at which you deliver value is one of your greatest advantages. But sometimes, connecting external development environments to cloud infrastructure forces a trade-off. Developers want to move fast with minimal setup, while IT teams need strict governance over data access.\n\nThe Agent Platform MCP server provides a single, standardized interface for your external agents so you can spend less time writing integration code and more time building useful features. And by running entirely within Google Cloud’s secure infrastructure, it gives you ready-to-use endpoints that protect your data while accelerating your development.\n\nGet the best of both worlds:\n\n**Enable the API**: The Gemini Enterprise Agent Platform remote MCP server is automatically enabled when you enable the Gemini Enterprise Agent Platform API within your Google Cloud project.\n\n2. **Configure your client**: Connect your AI application by following our [configuration instructions](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/use-agent-platform-mcp#configure-client) to point to the remote server.\n\n3. **Use toolsets**: Access a robust, copyable list of [Toolset Endpoints](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/mcp#expandable-1) to begin interacting with your Agent Platform resources immediately.\n\n|\n|\n||\n|\n|\n|\n|\n|\n/mcp/generate |\nGenerative AI tools |\nCore generation features |\n|\n/mcp/predict |\nPrediction tools |\nInference and raw prediction |\n|\n/mcp/notebook |\nColab enterprise notebook tools |\nNotebook runtime and execution management |\n|\n/mcp/endpoints |\nEndpoint management tools |\nLifecycle management for model endpoints |\n|\n/mcp/models |\nModel registry tools |\nModel upload, registry, and deployment |\n|\n/mcp/tuning |\nModel fine-tuning tools |\nFinetuning job management and tracking |\n|\n/mcp/evaluation |\nQuality evaluation tools |\nAutomated model quality and instance evaluation |\n|\n/mcp/prompts |\nPrompt management tools |\nPrompt engineering and versioning workflows |\n\nVisit the [Agent Platform page](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/use-agent-platform-mcp) to connect your favorite agent frameworks to the Agent Platform MCP server and start building today.", "url": "https://wpnews.pro/news/build-agents-even-faster-with-gemini-enterprise-agent-platforms-fully-managed", "canonical_source": "https://cloud.google.com/blog/products/ai-machine-learning/gemini-enterprise-agent-platform-remote-mcp-server/", "published_at": "2026-06-30 16:00:00+00:00", "updated_at": "2026-06-30 16:34:39.510009+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-infrastructure", "developer-tools", "generative-ai"], "entities": ["Google", "Gemini Enterprise Agent Platform", "MCP server", "Model Garden", "Antigravity CLI", "Claude Code", "Colab Enterprise"], "alternates": {"html": "https://wpnews.pro/news/build-agents-even-faster-with-gemini-enterprise-agent-platforms-fully-managed", "markdown": "https://wpnews.pro/news/build-agents-even-faster-with-gemini-enterprise-agent-platforms-fully-managed.md", "text": "https://wpnews.pro/news/build-agents-even-faster-with-gemini-enterprise-agent-platforms-fully-managed.txt", "jsonld": "https://wpnews.pro/news/build-agents-even-faster-with-gemini-enterprise-agent-platforms-fully-managed.jsonld"}}