How to Use the Nimbata MCP in Google ADK

Q: How do I register the Nimbata toolset in Google ADK?

Instantiate McpToolset with StreamableHttpServerParameters pointing to your Vinkius gateway URL. Pass this toolset object into the tools list when initializing your LlmAgent in Python.

Q: Can Google ADK process raw call audio from Nimbata?

Yes, the agent can use getcallrecording to fetch the MP3 file of a call. You can then feed this audio file directly into Gemini's multimodal API for transcription, summarization, and sentiment analysis.

Q: How do I restrict which Nimbata tools Google ADK can access?

Use the optional toolnames filter when setting up your McpToolset. For example, you can limit your agent to read-only tools like listcalls and getcallreport, blocking access to configuration tools like createsource.

Q: How do I search call histories using this server?

Your agent runs searchcalls with specific query filters like date ranges or tracking sources. This returns a structured list of call IDs that the agent can then inspect using getcalldetails.

Q: How does Google ADK protect customer phone numbers retrieved from Nimbata?

Raw phone numbers fetched via listnumbers or getcalldetails are processed within your private Google Cloud VPC. The Vinkius MCP Server gateway uses secure, ephemeral execution environments to ensure that customer contact details are never logged or cached outside your cloud perimeter.

Pipe offline phone conversion analytics directly into BigQuery and Gemini using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimbata MCP to Google ADK

Create your Vinkius account to connect Nimbata 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 Nimbata with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe Call Data to BigQuery with Google ADK

Your enterprise agent uses `list_calls` to pull hundreds of call records and formats them for immediate injection into BigQuery using Google ADK. This gives your database a direct line to raw offline phone conversions. Because Gemini handles huge token limits, the agent can parse hours of audio metadata returned by `get_call_details` in a single pass. You can run complex SQL queries against your offline call conversions alongside your online Google Ads data.

Automate Dynamic Number Insertion

Your agent uses `create_source` to provision tracking pools for enterprise landing pages on the fly using Google ADK. By wrapping this tool inside `McpToolset`, Google ADK exposes the exact parameters needed to map offline calls back to digital campaign IDs using the Nimbata MCP Server. Once a source is live, the agent runs `get_source` to verify routing targets. You can restrict the agent's scope by passing a filtered list of tools to the `tool_names` parameter, ensuring it only interacts with source creation.

Analyze Large Call Volumes

This integration uses `get_source_report` to feed aggregate performance metrics directly to Vertex AI models via Google ADK. The agent compares incoming call volumes against ad spend to flag underperforming tracking numbers. To dig deeper, the agent runs `get_call_report` to identify peak call times across different regions. This setup relies on `list_numbers` to audit your entire tracking inventory, ensuring every active campaign has an assigned local or toll-free number.

Setup guide

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

Instantiate `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius gateway URL. Pass this toolset object into the `tools` list when initializing your `LlmAgent` in Python.

Yes, the agent can use `get_call_recording` to fetch the MP3 file of a call. You can then feed this audio file directly into Gemini's multimodal API for transcription, summarization, and sentiment analysis.

Use the optional `tool_names` filter when setting up your `McpToolset`. For example, you can limit your agent to read-only tools like `list_calls` and `get_call_report`, blocking access to configuration tools like `create_source`.

Your agent runs `search_calls` with specific query filters like date ranges or tracking sources. This returns a structured list of call IDs that the agent can then inspect using `get_call_details`.

Raw phone numbers fetched via `list_numbers` or `get_call_details` are processed within your private Google Cloud VPC. The Vinkius MCP Server gateway uses secure, ephemeral execution environments to ensure that customer contact details are never logged or cached outside your cloud perimeter.

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