Google Agent Platform Docs
@OpenGerwin
About Google Agent Platform Docs
No overview available yet
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"google-agent-platform-docs": {
"command": "uvx",
"args": [
"mcp-google-agent-platform-docs"
]
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
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).
How does the server discover documentation pages?
It scans sitemaps on a weekly basis to automatically find new pages. The discovered structure is then cached for fast browsing and search.
Frequently asked questions
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).
How does the server discover documentation pages?
It scans sitemaps on a weekly basis to automatically find new pages. The discovered structure is then cached for fast browsing and search.
Basic information
More AI & Agents MCP servers
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
Transform MCP
UnstructuredThe Unstructured Transform MCP Server connects your ADK agent to Unstructured, a document processing platform that turns raw files into structured, AI-ready data. This integration gives your agent the ability to parse PD
Lumify Sports Intelligence
LumifyAgent-ready sports intelligence API: live scores, odds, line movement, public betting splits, and explainable bet confidence — via 16 MCP tools at https://lumify.ai/mcp. Get a free key instantly — no signup, email, or ca
Comments