How to Use the Laravel Forge MCP in AutoGen

Q: How do I register Laravel Forge tools via MCP with AutoGen agents?

You use the mcpservertools function from the autogen-ext package to load the tool definitions. You then pass this list of tools to your AssistantAgent constructor to let them execute commands.

Let AutoGen agents debate and coordinate Laravel Forge server deployments and worker configurations.

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 AutoGen

Create your Vinkius account to connect Laravel Forge to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate site deployments via AutoGen agent debate

The `deploy_site` tool commands a deployment script queue to execute on a repository site. In an AutoGen setup, a developer agent proposes a deployment while a QA agent reviews the site status before giving the green light. This multi-agent debate ensures that deployments only happen when specific conditions are met. The agents negotiate back and forth, using real-time tool outputs to reach a consensus.

Audit server recipes using AutoGen MCP Server tools

The `list_recipes` tool retrieves available custom shell recipes within your organizational team limits. An AutoGen security agent scans these recipes for outdated commands while a sysadmin agent schedules updates. This collaborative auditing prevents unsafe scripts from running on your servers. The agents discuss the risks of each recipe and agree on which ones are safe to execute.

Monitor worker queues with multi-agent consensus

The `list_workers` tool retrieves queue worker configurations executing on a tracked site. One agent monitors these worker counts while another agent checks server loads via `get_server`. If a queue is backed up, the agents debate whether to spin up more workers or upgrade the droplet. They analyze the data together and present you with a coordinated recommendation.

Setup guide

Set up Laravel Forge MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Laravel Forge tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Laravel Forge_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Laravel Forge data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Laravel Forge_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Laravel Forge data")
    print(result.messages[-1].content)

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 AutoGen

You use the mcp_server_tools function from the autogen-ext package to load the tool definitions. You then pass this list of tools to your AssistantAgent constructor to let them execute commands.

Yes, you configure a group chat where a security agent must approve the action. The deployment tool is only triggered once the AutoGen agents reach a consensus based on their conversation.

The McpToolAdapter automatically translates the MCP tool schemas into the format that AutoGen expects. This ensures that agents understand the parameters for tools like `get_site` without manual mapping.

Yes, AutoGen supports stdio and streamable HTTP transports for headless execution. You automate server checks and deployments as part of your automated testing workflow.

All API communication runs through a zero-trust, ephemeral V8 isolate that handles authentication. Your Forge API tokens and database lists are never stored or exposed to the individual AutoGen agents.

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