How to Use the Kontak MCP in Google ADK

Q: Can I limit which Kontak tools my Google ADK agent sees?

You sure can. Use the toolnames filter when setting up the toolset to restrict access. If you only want the agent sending texts, just expose sendoutboundsms.

Q: Does the agent know which tags apply to Kontak contacts?

It finds out by calling listkontaktags. The agent reads the available tags and can apply them to user profiles fetched via listkontakcontacts.

Q: How do I use Kontak templates with Gemini?

The agent calls listkontaktemplates to read the approved formats. It maps your Google Cloud data into the template variables before firing the message.

Give your Google ADK agents access to the Kontak MCP Server. Send texts, pull contact lists, and feed message logs directly into BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kontak MCP to Google ADK

Create your Vinkius account to connect Kontak 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 Kontak with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger texts from Google ADK

The `send_outbound_sms` tool connects your Gemini models to real-world phone networks. Your agent decides what to say based on your Vertex AI data, then fires the text message through the MCP Server. You do not have to write custom integration code. The agent formats the payload, hits the tool, and uses `list_kontak_messages` to confirm the outbound text hit the system queue.

Feed message history to BigQuery

The `get_message_details` and `list_kontak_messages` tools extract your entire communication history. Your Google ADK agent pulls these records and writes them straight to your data warehouse. Because Gemini handles massive context windows, you can fetch thousands of messages at once. The agent reads the block, structures the data, and preps it for your analytics pipelines.

Run automated system audits

Pulling security records happens through the `get_kontak_audit_logs` MCP tool. Your agent fetches the raw event data to track exactly who modified your account settings or contact lists. It can also call `get_kontak_account_info` and `list_kontak_webhooks` to verify your current infrastructure state. If a webhook points to an unauthorized URL, the agent flags it immediately.

Setup guide

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

Use the McpToolset class with StreamableHttpServerParameters pointing to your Vinkius URL. Pass that toolset directly into the tools array of your LlmAgent.

You sure can. Use the tool_names filter when setting up the toolset to restrict access. If you only want the agent sending texts, just expose send_outbound_sms.

It finds out by calling list_kontak_tags. The agent reads the available tags and can apply them to user profiles fetched via list_kontak_contacts.

The agent calls list_kontak_templates to read the approved formats. It maps your Google Cloud data into the template variables before firing the message.

The MCP protocol transmits raw SMS payloads and recipient phone numbers directly to your Gemini environment. The connection uses ephemeral tokens that expire instantly, ensuring no unauthorized client can intercept your communication logs.

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