How to Use the Dext MCP in Google ADK

Q: How does Google ADK handle large Dext document batches?

The Google ADK agent calls listinboxitems to retrieve the Dext inbox queue in chunks. Google ADK processes these items asynchronously, feeding the extracted text into Gemini for parallel analysis without hitting rate limits.

Q: Can Google ADK search Dext files using natural language?

Yes. The Google ADK agent uses searchinboxbykeyword to locate specific financial documents in Dext. You can ask your Google ADK agent to find all invoices from a specific vendor, and it will execute the search directly.

Q: Does Google ADK support Dext multi-tenant setups?

Yes. By utilizing listaccountingclients, your Google ADK agent can switch contexts between different Dext client accounts. This allows a single enterprise pipeline to manage bookkeeping for dozens of distinct businesses.

Q: How do I monitor Dext API usage limits in Google Cloud?

The Google ADK agent calls getaccountmetadata to retrieve your current Dext usage metrics. You can feed this data into Google Cloud Monitoring to set up alerts before you exceed your monthly document extraction limits.

Q: How is my extracted supplier and bank data protected?

All bank details from listconnectedbankaccounts and supplier names are processed through secure, read-only API calls. The MCP Server executes in an isolated V8 sandbox on Vinkius, ensuring your private ledger data never leaks to external training sets.

Feed Dext financial data directly to your Google ADK pipelines to automate enterprise bookkeeping and audit workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dext MCP to Google ADK

Create your Vinkius account to connect Dext 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 Dext with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track pending items using Google ADK

This MCP Server provides the `list_items_pending_review` tool to feed unprocessed receipt data directly into your Google ADK agent. This allows your Gemini models to analyze document context and match them against your BigQuery transaction tables. The Google ADK agent uses `get_item_details` to extract line-item details from complex Dext invoices. Because the Google ADK handles long contexts, you can pass years of historical Dext tax categories alongside the raw document text for highly accurate classification.

Manage client accounts via Google ADK

This MCP Server integration exposes `list_accounting_clients` to let your enterprise Google ADK agent manage multi-tenant bookkeeping pipelines in Dext. The agent queries your partner account, identifies active clients, and structures data extraction per client. The Google ADK agent then calls `list_account_users` to verify which staff members have access to the Dext client files. If a document fails extraction, the agent flags the specific user ID in your Google Cloud logging system for manual follow-up.

Categorize supplier invoices automatically

The `list_extracted_suppliers` tool retrieved through this MCP Server enables your Google ADK agent to match incoming Dext documents against known vendors. The agent cross-references these vendors with your Google Cloud SQL database to ensure consistency across systems. By querying `list_accounting_categories`, the Google ADK agent maps the extracted supplier to your specific Dext chart of accounts. This prevents duplicate entries and ensures that every invoice is categorized correctly before publication.

Setup guide

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

The Google ADK agent calls `list_inbox_items` to retrieve the Dext inbox queue in chunks. Google ADK processes these items asynchronously, feeding the extracted text into Gemini for parallel analysis without hitting rate limits.

Yes. The Google ADK agent uses `search_inbox_by_keyword` to locate specific financial documents in Dext. You can ask your Google ADK agent to find all invoices from a specific vendor, and it will execute the search directly.

Yes. By utilizing `list_accounting_clients`, your Google ADK agent can switch contexts between different Dext client accounts. This allows a single enterprise pipeline to manage bookkeeping for dozens of distinct businesses.

The Google ADK agent calls `get_account_metadata` to retrieve your current Dext usage metrics. You can feed this data into Google Cloud Monitoring to set up alerts before you exceed your monthly document extraction limits.

All bank details from `list_connected_bank_accounts` and supplier names are processed through secure, read-only API calls. The MCP Server executes in an isolated V8 sandbox on Vinkius, ensuring your private ledger data never leaks to external training sets.

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