Google Agent Platform Docs

Created By
OpenGerwin2 months ago
Overview

mcp-google-agent-platform-docs

MCP server providing Google AI platform documentation to AI agents.

Python 3.10+ MCP License: MIT

Part of OpenGerwin MCP Servers

What is this?

An MCP (Model Context Protocol) 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.

Instead of hallucinating API details, your AI assistant can look up the actual documentation in real-time.

Features

  • 🔍 Full-text search across 3400+ documentation pages
  • 📄 On-demand fetching — pages are downloaded and cached as you need them
  • 🗂️ Dual source — current GEAP + legacy Vertex AI documentation
  • Smart caching — 72-hour TTL, stale fallback on network errors
  • 🗺️ Auto-discovery — new pages found via sitemap scanning (weekly)
  • 🧩 Plug & play — works with Claude Desktop, Cursor, VS Code, any MCP client

Quick Start

Install

# Using pip
pip install mcp-google-agent-platform-docs

# Using uv (recommended)
uv pip install mcp-google-agent-platform-docs

Configure Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "google-agent-platform-docs": {
      "command": "mcp-google-agent-platform-docs"
    }
  }
}

Configure Antigravity (Google)

Add to ~/.gemini/antigravity/mcp_config.json:

{
  "mcpServers": {
    "google-agent-platform-docs": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcp-google-agent-platform-docs",
        "run",
        "mcp-google-agent-platform-docs"
      ]
    }
  }
}

Configure Cursor / VS Code

Add to your MCP settings:

{
  "mcpServers": {
    "google-agent-platform-docs": {
      "command": "mcp-google-agent-platform-docs",
      "transport": "stdio"
    }
  }
}

Tools

search_docs

Search documentation by keywords.

search_docs("Memory Bank setup", source="geap")
search_docs("function calling", source="vertex-ai")

get_doc

Get full content of a specific page.

get_doc("scale/memory-bank/setup", source="geap")
get_doc("multimodal/function-calling", source="vertex-ai")

list_sections

Browse documentation structure.

list_sections(source="geap")

list_models

Quick reference for all available AI models (Gemini, Imagen, Veo, Claude, etc.).

list_models()

Documentation Sources

Source IDPlatformPagesStatus
geapGemini Enterprise Agent Platform2300+Primary (current)
vertex-aiVertex AI Generative AI1100+Legacy (archive)

GEAP Sections

  • Agent Studio — Visual agent builder
  • Agents → Build — Runtime, ADK, Agent Garden, RAG Engine
  • Agents → Scale — Sessions, Memory Bank, Code Execution
  • Agents → Govern — Policies, Agent Gateway, Model Armor
  • Agents → Optimize — Observability, Evaluation, Quality Alerts
  • Models — Gemini, Imagen, Veo, Lyria, Partners, Open Models
  • Notebooks — Jupyter tutorials

Configuration

Environment variables for customization:

VariableDefaultDescription
MCP_DOCS_CACHE_DIR~/.cache/mcp-google-agent-platform-docsCache directory
MCP_DOCS_CONTENT_TTL72Page cache TTL (hours)
MCP_DOCS_STRUCTURE_TTL7Structure cache TTL (days)
MCP_DOCS_DEFAULT_SOURCEgeapDefault documentation source
MCP_DOCS_HTTP_TIMEOUT30HTTP timeout (seconds)

Development

# Clone
git clone https://github.com/OpenGerwin/mcp-google-agent-platform-docs.git
cd mcp-google-agent-platform-docs

# Install dependencies
uv sync

# Run server locally
uv run mcp-google-agent-platform-docs

# Test with MCP Inspector
uv run mcp dev src/mcp_google_agent_platform_docs/server.py

Architecture

mcp-google-agent-platform-docs/
├── sources/                    # YAML source configurations
│   ├── geap.yaml               # GEAP (primary)
│   └── vertex-ai.yaml          # Vertex AI (legacy)
├── src/mcp_google_agent_platform_docs/
│   ├── server.py               # FastMCP server + 4 tools
│   ├── source.py               # Source model (YAML loader)
│   ├── fetcher.py              # HTML → Markdown converter
│   ├── cache.py                # TTL cache manager
│   ├── discovery.py            # Sitemap-based page discovery
│   ├── search.py               # TF-IDF search engine
│   └── config.py               # Global configuration
└── tests/

License

MIT — see LICENSE.


Part of OpenGerwin MCP Servers

Server Config

{
  "mcpServers": {
    "google-agent-platform-docs": {
      "command": "uvx",
      "args": [
        "mcp-google-agent-platform-docs"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
a month ago
Author Name
OpenGerwin
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

10 hours ago