How to Use the Daftra MCP in Google ADK

Q: How do I connect the Daftra MCP Server to a Gemini agent using the Google ADK?

Install the SDK using pip install google-adk. Create an instance of McpToolset pointing to your Vinkius HTTP endpoint, and pass that toolset into your LlmAgent configuration to instantly discover tools like listinvoices and listexpenses.

Q: How does the Google ADK handle long-context accounting analysis with Daftra?

The ADK feeds the output of tools like listinvoices and listexpenses directly into Gemini's context window. Because Gemini supports over a million tokens, the agent can parse thousands of invoice lines and expense reports simultaneously to spot long-term financial trends.

Feed Daftra ERP records directly into Gemini's million-token context window using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daftra MCP to Google ADK

Create your Vinkius account to connect Daftra 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 Daftra with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise ERP intelligence with Google ADK

Gemini's massive context window lets you load your entire inventory catalog and invoice history at once. Your agent pulls inventory data using `list_inventory_products` and matches it against customer order histories retrieved via `list_invoices`. The Google ADK handles the data transfer, letting the model analyze years of sales data in a single turn. This setup lets you run complex forecasting without writing custom data pipelines. Your agent reads the raw product list, compares it to current sales trends, and identifies which stock items are underperforming. You get deep financial analysis directly inside your Google Cloud environment.

Connecting BigQuery data to Daftra via MCP Server

Combine your warehouse data with live ERP records. Your agent queries customer trends in BigQuery, then uses `search_clients_by_name` to find matching profiles in your ERP. Once it locates the right account, it calls `get_client_details` to verify their outstanding balance before initiating a marketing campaign. By exposing the MCP Server tools to your Gemini agent, you bridge the gap between cold storage data in BigQuery and active client records in your ERP. You get a unified view of your customer relations without manual exports.

Automated quote generation and pipeline tracking

Manage your sales pipeline directly from your agent workflows. The agent uses `list_estimates` to pull active quotes, checks the organizational settings with `get_site_metadata`, and updates sales reps on pending deals. It keeps your pipeline moving without manual CRM data entry. Because the ADK lets you restrict tools using a `tool_names` filter, you can lock down this agent. If you only want it handling quotes, limit its access to `list_estimates` and `get_site_metadata`, keeping your core accounting tools safe from accidental execution.

Setup guide

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

Install the SDK using `pip install google-adk`. Create an instance of `McpToolset` pointing to your Vinkius HTTP endpoint, and pass that toolset into your `LlmAgent` configuration to instantly discover tools like `list_invoices` and `list_expenses`.

Yes, you can use the ADK's built-in tool filtering. When instantiating your `McpToolset`, pass a list of allowed tool names to the configuration to expose safe lookup tools like `list_inventory_products` while completely hiding sensitive mutation tools like `create_client`.

The ADK feeds the output of tools like `list_invoices` and `list_expenses` directly into Gemini's context window. Because Gemini supports over a million tokens, the agent can parse thousands of invoice lines and expense reports simultaneously to spot long-term financial trends.

The ADK supports both Stdio and HTTP transports. While you can run a local daemon, using the Vinkius-hosted HTTP endpoint is the easiest way to keep your MCP connection alive without managing local node processes or SSH tunnels.

All billing details, client profiles, and expense logs pass directly between your Google Cloud environment and the Daftra API. Vinkius runs the connector in an ephemeral, zero-trust sandbox that never caches or logs your sensitive financial payloads.

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