Google Agent Platform Docs

Name: Google Agent Platform Docs
Author: OpenGerwin

@OpenGerwin

リポジトリ

Google Agent Platform Docs について

概要はまだありません

#vertex-ai-vertex-ai-api-google-agent-platform

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

公開者

OpenGerwin

投稿者

rrromochka

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": {
    "google-agent-platform-docs": {
      "command": "uvx",
      "args": [
        "mcp-google-agent-platform-docs"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

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 Google Agent Platform Docs?

An MCP server that gives AI agents direct access to Google's AI platform documentation — both the current Gemini Enterprise Agent Platform (GEAP) and the legacy Vertex AI Generative AI docs. It enables AI assistants to look up real-time documentation instead of hallucinating API details.

How to use Google Agent Platform Docs?

Install via pip install mcp-google-agent-platform-docs or uv pip install mcp-google-agent-platform-docs, then configure in any MCP client (Claude Desktop, Cursor, VS Code, Antigravity). The server provides four tools: search_docs, get_doc, list_sections, and list_models, invoked directly by the AI assistant.

Key features of Google Agent Platform Docs

Full-text search across 3400+ documentation pages
On-demand fetching with automatic caching
Dual source support (GEAP + Vertex AI)
Smart caching with 72-hour TTL and stale fallback
Auto-discovery of new pages via weekly sitemap scanning
Plug-and-play with any MCP client

Use cases of Google Agent Platform Docs

An AI agent looks up real-time API documentation to avoid hallucinating code examples
A developer browses the structure of Gemini Agent Platform docs to find relevant sections
An assistant retrieves the full content of a specific Vertex AI page for detailed guidance
An agent lists all available AI models across platforms for comparison

FAQ from Google Agent Platform Docs

What documentation sources are covered?

The server covers two sources: geap (Gemini Enterprise Agent Platform, 2300+ pages, primary) and vertex-ai (Vertex AI Generative AI, 1100+ pages, legacy archive).

How does caching work?

Pages are cached locally with a default 72-hour TTL (configurable via MCP_DOCS_CONTENT_TTL). On network errors, stale cached content is served as fallback. The documentation structure is cached separately with a 7-day default TTL.

What are the system requirements?

Python 3.10 or later and MCP 1.27.0 or later. The server uses stdio transport and works with any MCP-compatible client.

Can I configure the server's behavior?

Yes, via environment variables: MCP_DOCS_CACHE_DIR (cache location), MCP_DOCS_CONTENT_TTL (page cache hours), MCP_DOCS_STRUCTURE_TTL (structure cache days), MCP_DOCS_DEFAULT_SOURCE (default doc source), and MCP_DOCS_HTTP_TIMEOUT (HTTP timeout seconds).