How to Use the Diese MCP in Google ADK

Q: How do I initialize the Diese MCP Server within the Google ADK?

You instantiate an McpToolset using your server's HTTP endpoint URL. Pass this toolset directly into your LlmAgent constructor to give Gemini access to tools like listerpprojects and listprojecttasks.

Q: Can I use Gemini's 1M token context window with Diese data in Google ADK?

Yes, you can dump the entire payload of listresourceplanning or listsalesinvoices straight into the agent's context. The model handles the massive volume of ERP data easily, allowing you to ask complex questions about your entire resource history.

Q: How do I limit the agent to only view specific project names?

You use the native toolnames filter in your toolset configuration. The thing is, this allows you to expose only searchprojectsbyname and getprojectdetails while hiding financial tools like invoice lists.

Q: How is my Diese financial data protected when using this MCP Server?

Every request containing contacts from listerpcontacts or expenses from listbusinessexpenses is isolated inside a secure V8 environment. All traffic is encrypted in transit using TLS 1.3, and Vinkius never logs the actual payloads of your ERP queries.

Connect Gemini to your Diese ERP data using the Google ADK to analyze project lifecycles alongside your BigQuery datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Diese MCP to Google ADK

Create your Vinkius account to connect Diese 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 Diese with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Diese project tasks with Gemini long-context

The `diese-mcp` MCP Server exposes your active project data to Gemini models so you can feed thousands of task logs into a single prompt. By passing `list_project_tasks` and `list_resource_planning` to your LlmAgent, you can analyze months of scheduling history without hitting context window limits. The model processes this massive dataset to find bottlenecks in your resource allocation. This integration lets you run complex reasoning tasks over your entire operations database. Your agent reads every entry returned by `list_overdue_erp_tasks` and compares it against historical deadlines. You get a clear picture of project health without manually exporting spreadsheets or writing custom database queries.

Join ERP data with BigQuery using this MCP Server

Your Google ADK agents can query live ERP data using `list_business_expenses` via this MCP connection. The agent calls `list_business_expenses` to pull current operational costs, then runs a SQL query on your warehouse to calculate profit margins. This bridges the gap between active transactional data and long-term business intelligence. You set up a single `McpToolset` that exposes tools like `list_sales_invoices` directly to your Gemini-powered agent. The agent handles data transformations in memory, converting raw JSON payloads into structured inputs for your cloud analytics pipelines. This eliminates the need for nightly ETL jobs just to get basic financial metrics.

Enterprise identity mapping for project contacts

This server maps your Google Cloud IAM roles to your ERP directory using `list_erp_contacts` to control access to sensitive business records. When your agent invokes `list_erp_contacts` or `get_project_details`, the request carries the user's authenticated session. This ensures that only authorized team members can view partner details and project budgets. Vinkius manages the underlying OAuth handshake, so your Python application doesn't have to handle token rotation. Your agent gets a clean, authenticated channel to `get_account_metadata` to verify API usage limits. You maintain strict enterprise security standards while giving your models direct access to operational tools.

Setup guide

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

You instantiate an `McpToolset` using your server's HTTP endpoint URL. Pass this toolset directly into your `LlmAgent` constructor to give Gemini access to tools like `list_erp_projects` and `list_project_tasks`.

Yes, you can dump the entire payload of `list_resource_planning` or `list_sales_invoices` straight into the agent's context. The model handles the massive volume of ERP data easily, allowing you to ask complex questions about your entire resource history.

Yes, you can connect using either transport method depending on your deployment architecture. For cloud-hosted enterprise agents, the streamable HTTP transport is the recommended way to interact with the server.

You use the native `tool_names` filter in your toolset configuration. The thing is, this allows you to expose only `search_projects_by_name` and `get_project_details` while hiding financial tools like invoice lists.

Every request containing contacts from `list_erp_contacts` or expenses from `list_business_expenses` is isolated inside a secure V8 environment. All traffic is encrypted in transit using TLS 1.3, and Vinkius never logs the actual payloads of your ERP queries.

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