How to Use the Karbon MCP in Google ADK

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

Use pip install google-adk and create an McpToolset using StreamableHttpServerParameters. Pass this toolset into your LlmAgent tools array to expose the endpoints.

Q: Can a Google ADK agent create new Karbon contacts automatically?

Yes. The agent can call createcontact directly from its workflow. It just needs to provide a name and specify whether the contact is a Person or Organization.

Q: How do I limit which Karbon tools my Google ADK agent can use?

Provide a toolnames list when setting up the McpToolset. This ensures the agent only sees the specific functions you allow, like getworkitem, ignoring the rest.

Q: Will this integration work with my existing Vertex AI pipelines?

Absolutely. You can pull CRM data using listcontacts and feed those records straight into your custom Vertex models for analysis or risk scoring.

Connect Gemini agents to your firm's workflows using Google ADK and act on accounting data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Karbon MCP to Google ADK

Create your Vinkius account to connect Karbon 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 Karbon with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Karbon data into Google ADK agents

Gemini models can hold millions of tokens, meaning your Google ADK agent can ingest massive amounts of firm history at once. You can run `list_work_items` and `list_contact_notes` to pull entire client histories directly into the prompt context. This MCP integration bridges your accounting operations with Google Cloud infrastructure. The agent cross-references BigQuery datasets against the results from `list_organizations`, giving your enterprise a complete view of client profitability.

Manage work items via MCP Server

Your enterprise agents don't just read data—they execute workflows. When a new contract lands in Google Workspace, your LlmAgent can trigger `create_work_item` to immediately spin up the corresponding tax or audit project. You can also track task progress autonomously. The agent loops through `list_work_tasks` for a specific project and uses `update_work_item` to adjust statuses based on what it finds in Vertex AI document pipelines.

Filter tool exposure for specialized agents

Not every agent needs full access to your CRM. Google ADK lets you pass an optional `tool_names` filter to the `McpToolset` constructor, restricting a specific agent to just `list_people` and `get_contact`. This creates clean separation of concerns. You might have one restricted agent handling external client queries while a separate internal operations agent holds permissions to run `create_contact` and assign team members via `list_users`.

Setup guide

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

Use `pip install google-adk` and create an `McpToolset` using `StreamableHttpServerParameters`. Pass this toolset into your `LlmAgent` tools array to expose the endpoints.

Yes. The agent can call `create_contact` directly from its workflow. It just needs to provide a name and specify whether the contact is a Person or Organization.

Provide a `tool_names` list when setting up the `McpToolset`. This ensures the agent only sees the specific functions you allow, like `get_work_item`, ignoring the rest.

Absolutely. You can pull CRM data using `list_contacts` and feed those records straight into your custom Vertex models for analysis or risk scoring.

Ephemeral architecture ensures zero persistence of your sensitive tax workflows and contact notes. The MCP connection operates in a zero-trust sandbox, so the records fetched by `list_work_tasks` never linger on disk.

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