How to Use the Moxie MCP in Google ADK

Q: How do I use Google ADK to generate Moxie invoices for all active projects?

Your agent would first call searchprojects with status='active'. It then iterates through the results, calling createinvoice for each project that has unbilled hours. The long context of Gemini models helps manage this for many projects at once.

Q: Can my agent filter the tools from the Moxie MCP Server when using Google ADK?

Yes, the Google ADK's McpToolset constructor accepts a toolnames filter. This lets you expose only specific tools, like createtask, to an agent designed for a specific purpose like internal support.

Q: What's the process for adding a new client in Moxie using a Google ADK agent?

The agent simply calls the createclient tool with the required name and contact info. You can build a flow where it first uses searchcontacts to prevent creating a duplicate record, which is good practice for data hygiene.

Connect Google's Gemini agents to your agency's data. Run your business on Moxie, automated with the Google ADK and your GCP stack.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moxie MCP to Google ADK

Create your Vinkius account to connect Moxie 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 Moxie with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Clients and Projects at Scale

The Moxie toolset for Google ADK plugs your agent directly into your business operations. Your Gemini-powered agent can query your CRM in BigQuery, then use `create_client` and `create_project` in Moxie to formalize the new engagement. This creates a direct link between your sales data and your operational platform. Your agent can `search_projects` by status and sync that information back to a Google Sheet or Data Studio dashboard for real-time reporting through a single MCP connection.

Financial Automation with Google ADK

Let your agent handle the billing cycle. It can monitor project progress and use `create_time_entry` to log hours automatically from developer commits or calendar events. You can also feed it expense reports to log with `create_expense`. At the end of the month, the agent can `search_invoices` to see what's outstanding, then `create_invoice` for all billable work. Because Google ADK integrates with Vertex AI, you can build sophisticated logic to handle complex billing rules without leaving your GCP environment.

Integrate Moxie Tasks with Your CI/CD

Use this MCP Server to bridge your development pipeline and your project management. A post-deployment script can trigger your agent to `create_task` in Moxie for the QA team. This keeps your business and technical teams in sync. You can also build support bots. An agent can monitor a support channel, parse user requests, and `create_ticket` in Moxie, assigning it to the right person from the `list_users` tool. This brings your support workflow into your automated Google Cloud ecosystem.

Setup guide

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

Your agent would first call `search_projects` with `status='active'`. It then iterates through the results, calling `create_invoice` for each project that has unbilled hours. The long context of Gemini models helps manage this for many projects at once.

Yes, the Google ADK's `McpToolset` constructor accepts a `tool_names` filter. This lets you expose only specific tools, like `create_task`, to an agent designed for a specific purpose like internal support.

The agent simply calls the `create_client` tool with the required name and contact info. You can build a flow where it first uses `search_contacts` to prevent creating a duplicate record, which is good practice for data hygiene.

Instead of writing boilerplate HTTP request code, you just give the agent the toolset. The Google ADK handles the API calls, authentication, and error handling, so you can focus on the business logic of your agent.

It processes operational data: client and contact info, project details, tasks, support tickets, time entries, and invoices. Your connection is secured through a Vinkius token, and the server runs in an ephemeral, zero-trust sandbox, so your GCP and Moxie credentials are never directly linked.

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