How to Use the Callpicker MCP in Google ADK

Q: How do I get started with Callpicker and Google ADK?

After pip install google-adk, create an McpToolset instance pointing to your Vinkius server URL. Then, just pass that toolset in the tools list when you build your LlmAgent.

Q: Can I use Callpicker with Google ADK to analyze call performance in BigQuery?

Yes, that's a primary use case. An agent can use getcdrreport from Callpicker to fetch data, then use Google Cloud tools to load and query it in BigQuery.

Q: How do I limit which Callpicker tools my Google ADK agent can access?

The McpToolset has a toolnames parameter. You can provide a specific list of tool names, like 'makecall', 'listcalllogs', to restrict the agent's capabilities.

Connect your Google ADK agents to your phone system to analyze call data and act on it, right from your GCP environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Callpicker MCP to Google ADK

Create your Vinkius account to connect Callpicker 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 Callpicker with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Call Data into BigQuery

Stop manually exporting and importing call data. Your Google ADK agent can use `get_cdr_report` to pull thousands of call records directly from your phone system. From there, it's a straight shot into a BigQuery table. You already live in Google Cloud. This MCP Server lets your agents bridge the gap between your communications stack and your data warehouse. Build an agent that automatically syncs call logs every hour, enriching your existing customer datasets in BigQuery without any manual work.

Enterprise Call Automation on GCP

Manage your phone infrastructure at scale. An agent running on Google ADK can use `list_virtual_numbers` to find available DIDs or audit configured lines with `list_pbx_extensions`. It can even kick off a call with `make_call` as part of a larger workflow. Think of it as an extension of your existing Google Cloud automation. Your agent can react to a Cloud Monitoring alert, check the PBX status with `get_pbx_system_status`, and then use Callpicker to reroute calls or notify an admin, all within the same trusted environment.

Analyze Huge Call Logs with Google ADK

Gemini models can handle massive contexts. This changes how you work with call data. Your agent can fetch a complete, multi-megabyte call detail report with `get_cdr_report` and analyze the entire thing in a single prompt. Ask complex questions about the raw data. For example: 'Using this CDR report, find the top 10 numbers with the longest average call duration in the last quarter and cross-reference them with our high-value customer list.' Your agent can hold the entire dataset in its context to find the answer.

Setup guide

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

After `pip install google-adk`, create an `McpToolset` instance pointing to your Vinkius server URL. Then, just pass that toolset in the `tools` list when you build your `LlmAgent`.

Yes, that's a primary use case. An agent can use `get_cdr_report` from Callpicker to fetch data, then use Google Cloud tools to load and query it in BigQuery.

It does. The Callpicker tools are exposed to any Gemini model you've configured. This lets you use Gemini's long-context reasoning to analyze call logs and system status reports.

The `McpToolset` has a `tool_names` parameter. You can provide a specific list of tool names, like `['make_call', 'list_call_logs']`, to restrict the agent's capabilities.

Your data is secure. The MCP server runs in a zero-trust sandbox on Vinkius. It only processes call metadata and recording URLs, never the raw audio content, which remains on your own infrastructure.

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