How to Use the Botsonic MCP in Google ADK

Q: How do I initialize Botsonic with the Google ADK?

Install google-adk and configure McpToolset using your Vinkius HTTP endpoint. Pass that toolset into your LlmAgent tools array, and Gemini will automatically discover the MCP tools.

Q: Can I limit which Botsonic tools my Google ADK agent can access?

Yes. Use the toolnames filter when setting up your McpToolset. This lets you restrict sensitive tools like updatebot while still letting the agent read data via getbot.

Q: How do I update Botsonic bot settings using Google ADK?

Your agent can call updatebot to adjust bot configurations on the fly. It reads the current settings with getbot, decides on the changes, and applies them instantly.

Feed your Gemini agents real-time support data by hooking the Google ADK up to your Botsonic platform.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Botsonic MCP to Google ADK

Create your Vinkius account to connect Botsonic 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 Botsonic with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise Knowledge Sync via Google ADK

This MCP Server connects your enterprise AI pipelines directly to your support bots using `add_knowledge_url` and `list_knowledge_base`. Your Gemini models can read updated documentation from your Google Cloud storage and push those new URLs directly into your bot's training set. The agent verifies the pipeline's status using `check_botsonic_status` to ensure the bot digested the new files. This keeps your customer-facing bots updated with your latest product specs without manual uploads.

Deep Support Analytics in Google Cloud

Your agent can pull performance metrics using `get_bot_analytics` and pipe them straight into BigQuery. By combining support data with your internal tables, you get a complete picture of customer satisfaction. You can also call `list_bots` to inventory all active virtual agents across your enterprise. The agent can automatically flag underperforming bots and queue them for training updates based on real usage data.

Direct Lead Capture and Routing

Use `list_leads` to extract contact details from your support widgets and send them to your enterprise databases. Your Google ADK agent pulls these leads as structured data, ready for immediate sales routing. If a lead requires custom follow-up, the agent can fetch the original chat context using `get_conversation`. Having the full chat history lets your sales team know exactly what the customer asked before making the first call.

Setup guide

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

Install `google-adk` and configure `McpToolset` using your Vinkius HTTP endpoint. Pass that toolset into your `LlmAgent` tools array, and Gemini will automatically discover the MCP tools.

Yes. Use the `tool_names` filter when setting up your `McpToolset`. This lets you restrict sensitive tools like `update_bot` while still letting the agent read data via `get_bot`.

Absolutely. Your Google ADK agent can ingest massive knowledge bases and selectively feed relevant URLs to `add_knowledge_url` without running out of context window.

Your agent can call `update_bot` to adjust bot configurations on the fly. It reads the current settings with `get_bot`, decides on the changes, and applies them instantly.

Vinkius runs this MCP Server inside a zero-trust, ephemeral sandbox. Your knowledge base URLs and bot configurations are only fetched to execute the requested tool and are never cached or exposed to external networks.

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