How to Use the Konnektive MCP in Google ADK

Q: How do I initialize the Konnektive MCP Server in Google ADK?

Install the google-adk package. Configure a McpToolset with your Vinkius HTTP endpoint and pass it to your LlmAgent tools list.

Q: Can Google ADK agents search for specific Konnektive orders?

They can. The querykonnektiveorders tool accepts JSON filters. Your agent searches by date, status, or customer ID natively.

Q: Is it possible to restrict which Konnektive MCP tools the Google ADK agent sees?

Yes. Use the toolnames filter in your McpToolset setup. You might only want an agent to access getorderdetails while blocking write actions.

Q: How does Konnektive work with Gemini's long context?

You can pull massive datasets. Run querykonnektivetransactions with broad filters and let Gemini analyze the entire JSON payload at once.

Bring Konnektive data into Google ADK. Build Gemini agents that query transactions, update shipping addresses, and manage orders at scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Konnektive MCP to Google ADK

Create your Vinkius account to connect Konnektive 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 Konnektive with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Konnektive data into Google ADK

This Konnektive MCP integration feeds raw CRM context directly into your enterprise ecommerce pipelines. When a customer emails about a delayed package, your agent runs `query_konnektive_customers` and cross-references the results against your existing BigQuery tables. Gemini's massive context window means you can dump hundreds of records at once. Have the agent pull `query_konnektive_transactions` for an entire cohort and analyze payment patterns without hitting token limits.

Audit logs and order resolution

This server lets you instantly figure out who touched an account last during a support escalation. Stop clicking through CRM menus. Your agent executes `get_konnektive_audit_logs` to reconstruct the exact timeline of events for any disputed order. Once the issue is identified, the agent takes action. If a package is heading to the wrong state, it triggers `update_order_shipping_address` to fix it instantly. You resolve the problem in seconds instead of hours.

Map fulfillment and campaigns

This MCP Server exposes exactly how your products and campaigns are structured. By calling `list_billing_campaigns`, your agent maps out your active marketing funnels for Vertex AI. It then uses `list_fulfillment_houses` and `list_konnektive_products` to understand where those items physically sit. You get a complete, automated view of your supply chain straight from the source.

Setup guide

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

Install the `google-adk` package. Configure a `McpToolset` with your Vinkius HTTP endpoint and pass it to your `LlmAgent` tools list.

They can. The `query_konnektive_orders` tool accepts JSON filters. Your agent searches by date, status, or customer ID natively.

Yes. Use the `tool_names` filter in your `McpToolset` setup. You might only want an agent to access `get_order_details` while blocking write actions.

You can pull massive datasets. Run `query_konnektive_transactions` with broad filters and let Gemini analyze the entire JSON payload at once.

The server processes raw payment transaction logs and order histories. Vinkius routes these payloads through ephemeral V8 sandboxes directly to your Google Cloud environment, ensuring no persistent caching of financial records.

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