How to Use the Daftra MCP in Google ADK

Q: How do I restrict the Daftra tools visible to my Google ADK agent?

Use the toolnames filter when initializing your MCP Server toolset in Python. This lets you expose only listproducts or createinvoice while keeping treasury tools hidden from public-facing agents.

Q: Can I combine Daftra data with BigQuery using Google ADK?

Yes. Your agent can pull client histories using listclients and join that data with Google Cloud datasets. Gemini's long context handles the combined dataset to find regional purchasing trends.

Q: Will the Daftra MCP Server work with Gemini's 1M token context?

Yes. Your Google ADK agent can ingest large payloads from listinvoices without running out of memory. This lets the model spot long-term unpaid accounts across thousands of historical records.

Feed your Daftra ERP data directly into Gemini enterprise workflows 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

Analyze regional business expenses in BigQuery

The `list_expenses` and `list_treasuries` tools pull financial records directly from your Daftra account into the Google ADK environment using our secure MCP Server. This allows Gemini to cross-reference your Middle East cash flow against warehouse logs stored in Google Cloud. Because Gemini handles massive token contexts, your agent reads years of expense history in a single prompt. It maps outbound payments against regional tax rules to prepare your quarterly reports automatically.

Automate MENA stock reordering via Google ADK

The `list_products` tool connects your live inventory catalog to Gemini's reasoning engine via MCP. Your Google ADK agent monitors stock counts and triggers reorder drafts when items run low. You can restrict the agent's scope by filtering tools in the toolset constructor to expose only product tools. This ensures the inventory agent cannot access sensitive salary or treasury data while managing your warehouse.

Generate customer invoices from CRM activities

Your agent calls `create_invoice` and `get_invoice` to bridge the gap between your customer interactions and your billing ledger. When a sales contract closes in Vertex AI, the agent instantly drafts the corresponding billing document in Daftra. Using the HTTP transport, your Google ADK agent queries `list_clients` to verify the buyer's tax profile before generating the document. This prevents billing errors and speeds up your regional collection cycle.

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

Use the tool_names filter when initializing your MCP Server toolset in Python. This lets you expose only `list_products` or `create_invoice` while keeping treasury tools hidden from public-facing agents.

Yes. Your agent can pull client histories using `list_clients` and join that data with Google Cloud datasets. Gemini's long context handles the combined dataset to find regional purchasing trends.

The SDK connects to a single secure Vinkius HTTP endpoint using a token. You do not expose your raw API keys to the LLM agent, keeping your financial gateway protected.

Yes. Your Google ADK agent can ingest large payloads from `list_invoices` without running out of memory. This lets the model spot long-term unpaid accounts across thousands of historical records.

All traffic between Google ADK and Daftra passes through isolated V8 sandboxes on the MCP host. Your raw client profiles, payment logs, and product prices are encrypted in transit and never used to train Google's models.

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