How to Use the Holded MCP in Google ADK

Q: How do I initialize the Holded MCP Server with Google ADK?

Install google-adk via pip. Wrap the Vinkius URL in McpToolset and pass it to your LlmAgent under the tools parameter.

Q: Can my Google ADK agent read Holded contact details?

It uses getcontactdetails to pull specific client profiles. Gemini can then match those profiles against customer records you already store in Vertex AI.

Q: How do I prevent my agent from accidentally updating Holded stock in Google ADK?

Use the toolnames filter in Google ADK. You can restrict the agent to read-only tools like listproducts and block access to updateproductstock.

Q: Does this MCP integration work with Gemini's long context window?

Yes. You can loop through listinvoices to pull hundreds of records. Gemini handles the massive payload without dropping details.

Feed your Holded data directly into Gemini using Google ADK to analyze massive project lists and inventory logs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Holded MCP to Google ADK

Create your Vinkius account to connect Holded 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 Holded with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze project tasks with Google ADK

The `list_all_tasks` and `list_projects` tools dump your entire operational history into Gemini's massive context window. Your Google ADK agent can ingest thousands of task descriptions at once. You do not have to worry about chunking or vectorizing this data. Gemini reads the raw output from the MCP integration and cross-references it with your existing BigQuery datasets to spot delays in project delivery.

Sync billing records to your cloud

Fetching `list_invoices` and `get_invoice_details` allows your agent to pull line-by-line financial data from Holded. The agent reads the exact amounts, dates, and client IDs. Connect this to your Google Cloud infrastructure. You can build an automated pipeline where an agent pulls yesterday's invoices and writes the summaries directly into your enterprise data warehouse.

Control Holded stock levels

The `list_products` and `update_product_stock` tools let your Gemini agent monitor and adjust your warehouse inventory. It reads the current stock and writes back new quantities as needed. Setup requires passing the Vinkius endpoint to `McpToolset` using `StreamableHttpServerParameters`. Once injected into your `LlmAgent`, it handles the HTTP transport automatically. You can filter the exposed MCP Server tools if you only want the agent to read data.

Setup guide

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

Install `google-adk` via pip. Wrap the Vinkius URL in `McpToolset` and pass it to your `LlmAgent` under the tools parameter.

It uses `get_contact_details` to pull specific client profiles. Gemini can then match those profiles against customer records you already store in Vertex AI.

Use the `tool_names` filter in Google ADK. You can restrict the agent to read-only tools like `list_products` and block access to `update_product_stock`.

Yes. You can loop through `list_invoices` to pull hundreds of records. Gemini handles the massive payload without dropping details.

The connection routes through a zero-trust V8 Isolate Sandbox. When your agent requests names and tax IDs from `list_contacts`, the data is processed ephemerally. Vinkius stores zero payload data.

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