広告掲載
MCP.so
ログイン

Vertex AI MCP Server

@shariqriazz

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

shariqriazz

Vertex AI MCP Server について

概要はまだありません

Vertex AI MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "vertex-ai-mcp-server": {
      "command": "bun",
      "args": [
        "run",
        "build"
      ]
    }
  }
}

Vertex AI MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Vertex AI MCP Server?

Vertex AI MCP Server is a Model Context Protocol (MCP) server that provides a comprehensive suite of tools for interacting with Google Cloud's Vertex AI Gemini models, focusing on coding assistance and general query answering.

How to use Vertex AI MCP Server?

Install dependencies with bun install, build with bun run build, then run via bunx vertex-ai-mcp-server or configure it in your MCP client (e.g., Cline) by specifying the command and environment variables. Required configurations include setting AI_PROVIDER and either GOOGLE_CLOUD_PROJECT (for Vertex) or GEMINI_API_KEY (for Gemini).

Key features of Vertex AI MCP Server

  • Provides AI-powered query answering with and without web search grounding.
  • Offers 20+ specialized tools for code analysis, documentation, security, and architecture.
  • Supports filesystem operations (read, write, edit, move, search files).
  • Combines AI generation with filesystem actions for saving results.
  • Configurable model ID, temperature, streaming, and retry settings via environment variables.
  • Uses streaming API by default with basic retry logic for transient errors.

Use cases of Vertex AI MCP Server

  • Answer technical questions using Google Search‑enhanced or direct AI knowledge.
  • Analyze code snippets for bugs, performance issues, and security vulnerabilities.
  • Generate structured project guidelines, documentation, and testing strategies.
  • Compare technologies and recommend architecture patterns for specific domains.
  • Perform filesystem tasks (read, write, edit, organize files) alongside AI assistance.

よくある質問

1

What models does Vertex AI MCP Server use?

It provides tools for Vertex AI Gemini models, configurable via the `VERTEX_MODEL_ID` or `GEMINI_MODEL_ID` environment variables.

2

What are the prerequisites?

Node.js v18+, Bun installed globally, a Google Cloud project with billing and Vertex AI API enabled, and configured authentication (Application Default Credentials or a service account key).

3

Can I use it without a Google Cloud project?

Yes, set `AI_PROVIDER` to `"gemini"` and provide a `GEMINI_API_KEY` instead of a Google Cloud project.

4

What authentication methods are supported?

For Vertex AI, use Application Default Credentials (recommended via `gcloud auth application-default login`) or a service account key set via `GOOGLE_APPLICATION_CREDENTIALS`.

5

How do I customize the AI behavior?

Set environment variables such as `AI_TEMPERATURE`, `AI_USE_STREAMING`, `AI_MAX_OUTPUT_TOKENS`, `AI_MAX_RETRIES`, and `AI_RETRY_DELAY_MS` when configuring the MCP client.

コメント

「その他」の他のコンテンツ

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

広告掲載