How to Use the Laravel Forge MCP in Google ADK

Q: How do I configure Laravel Forge tools in Google ADK?

Initialize McpToolset with your Vinkius HTTP endpoint in your Python environment. Pass that toolset into your LlmAgent initialization to make the Forge tools available to Gemini.

Q: Does Google ADK support all nine Laravel Forge MCP tools?

Yes, the ADK automatically discovers every tool from listservers to listworkers. You filter the tools using the toolnames parameter if you want to limit Gemini's capabilities.

Q: How does the Google ADK handle long-context reasoning with Laravel Forge data?

Gemini models process the outputs of listsites and listdatabases in a single context window. This allows the agent to reason about complex multi-server environments without losing track of details.

Manage Laravel Forge servers and databases directly from enterprise Google ADK agents using Gemini models via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Laravel Forge MCP to Google ADK

Create your Vinkius account to connect Laravel Forge to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Laravel Forge with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Laravel Forge server health with Google ADK

The `get_server` tool retrieves detailed configuration specs for your Forge droplets. The Google ADK feeds this raw infrastructure data directly into Gemini's long-context window, letting the model analyze server specs alongside your Google Cloud resource metrics. If a server runs low on resources, the agent calls `list_sites` to identify which web apps are hosted on that specific machine. This allows your Google Cloud enterprise pipeline to make resource allocation decisions.

Run `deploy_site` via Gemini enterprise agents

The `deploy_site` tool triggers repository deployment scripts on your Forge sites via our MCP Server. Google ADK maps this tool to your `LlmAgent`, allowing Gemini to execute deployments after verifying build logs stored in BigQuery. You restrict access by passing a filtered list of tools to the `McpToolset` constructor. This ensures your agent can deploy code but cannot inspect sensitive data via `list_databases`.

Map custom shell scripts using Google ADK toolsets

The `list_recipes` tool fetches your team's custom provision scripts from Forge. Google ADK exposes these scripts directly to Gemini, letting the agent determine which recipe to run based on current server states. The agent verifies active keys using `list_ssh_keys` before recommending any script execution. This combines Google's enterprise security context with your active Forge configurations.

Setup guide

Set up Laravel Forge MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Laravel Forge tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Laravel Forge_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Laravel Forge tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Laravel Forge. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Laravel Forge now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Laravel Forge MCP in Google ADK

Initialize `McpToolset` with your Vinkius HTTP endpoint in your Python environment. Pass that toolset into your `LlmAgent` initialization to make the Forge tools available to Gemini.

Yes, you trigger the agent when a BigQuery table updates, which then executes `deploy_site` on your target Forge server. This automates your continuous integration pipeline directly from your GCP data warehouse.

Yes, the ADK automatically discovers every tool from `list_servers` to `list_workers`. You filter the tools using the `tool_names` parameter if you want to limit Gemini's capabilities.

Gemini models process the outputs of `list_sites` and `list_databases` in a single context window. This allows the agent to reason about complex multi-server environments without losing track of details.

Your credentials remain securely stored in the Vinkius vault and are never exposed to the Google ADK client. The MCP Server acts as a secure intermediary, transmitting only the structured JSON outputs of your server configurations and deployment statuses.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript