How to Use the Front MCP in Google ADK

Q: How do I connect the Front MCP server to a Google ADK agent?

You'll use the McpToolset class from the google-adk library, passing it the server URL we provide. Then you add that toolset to your LlmAgent's tools list.

Q: Can my Google ADK agent manage multiple Front inboxes?

Yes. The listsharedinboxes tool gives your agent a list of all available inboxes. It can then use the inbox ID to listconversations for a specific team, like 'Support' or 'Sales'.

Connect your Google ADK agents to Front. Let Gemini models reason over your customer conversations and act on them through your GCP environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Front MCP to Google ADK

Create your Vinkius account to connect Front 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 Front with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Give Gemini Access to Front Data

This server acts as a bridge between your Google ADK agent and your Front account. Your agent can pull entire message histories with `list_conversation_messages` or get a high-level view with `list_conversations`. It's the raw data your Gemini model needs to understand context. Because Google ADK is built for long context, you can feed huge amounts of conversation data into your agent. It can analyze patterns across dozens of threads to decide on the best action, like using `update_conversation_status` to tag an issue for escalation.

Build Enterprise Workflows in GCP

The real point here is integrating Front into your existing Google Cloud stack. An agent can pull contact data with `list_team_contacts`, cross-reference it with customer data in BigQuery, and then decide whether to `reply_to_conversation`. You aren't just building a chatbot. You're building an enterprise process. For example, an agent could use `search_conversations_by_query` to find all conversations about a specific outage, summarize them, and then create a new incident. This MCP server is the first step.

A Managed Toolset for Google ADK

Setting this up is simple. You create an `McpToolset` pointing to the server URL. The ADK framework handles the rest, making tools like `list_shared_inboxes` and `get_contact_info` available to your agent. You can even filter which tools are exposed. If you want a read-only agent, just give it the `list_*` and `get_*` tools. This prevents it from accidentally sending messages or changing conversation states, giving you a safe way to start.

Setup guide

Set up Front 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 Front 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="Front_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Front 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 Front. 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 Front 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 Front MCP in Google ADK

You'll use the `McpToolset` class from the `google-adk` library, passing it the server URL we provide. Then you add that toolset to your `LlmAgent`'s `tools` list.

Yes. The `list_shared_inboxes` tool gives your agent a list of all available inboxes. It can then use the inbox ID to `list_conversations` for a specific team, like 'Support' or 'Sales'.

If you're already on Google Cloud, yes. The ability to combine this server with other GCP tools is the main advantage. Your agent can talk to Front, then talk to BigQuery, all within the same session.

If the Front API returns an error, this MCP server passes it cleanly to your agent. Your agent's logic won't crash; it will receive an error that it can handle, for example, by retrying a call to `reply_to_conversation`.

Your agent gets access to whatever your Front API token can see. This includes customer conversation text via `get_message_content` and contact details through `get_contact_info`. Vinkius isolates each server instance, but the data is flowing from Front to your agent in GCP, so your cloud security policies apply.

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