How to Use the MightyCall MCP in Google ADK

Q: How do I configure MightyCall with the Google ADK?

Use the McpToolset class with your Vinkius HTTP endpoint and pass it to your LlmAgent tools parameter. This exposes tools like listcalls and listcontacts directly to your Gemini-powered agent.

Q: Can Google ADK agents trigger outbound dialing through MightyCall?

Yes, the agent can invoke the makecall tool to initiate outbound calls. You can restrict this tool using the toolnames filter in your ADK setup if you only want the agent to read data.

Q: Does this MCP Server support Gemini's 1M token context?

Yes, you can pass large lists of call histories from listcalls directly into Gemini's massive context window. The agent can analyze hours of phone metadata in a single run.

Q: How do I limit which MightyCall tools my Google ADK agent can see?

Use the toolnames parameter in the StreamableHttpServerParameters config. This lets you block tools like makecall while keeping read-only tools like listvoicemails active.

Q: What happens to my MightyCall contact data when using this MCP Server?

Your contact records retrieved via listcontacts are transmitted through encrypted HTTPS channels directly to your Google Cloud environment. Vinkius runs the server in an ephemeral sandbox, meaning no contact names or phone numbers are cached on our servers.

Connect MightyCall phone operations directly to BigQuery and Vertex AI workflows using Google ADK agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MightyCall MCP to Google ADK

Create your Vinkius account to connect MightyCall 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 MightyCall with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze call logs using Google ADK and BigQuery

Your Google ADK agent pulls raw telephone records using `list_calls` and feeds them straight into your Cloud SQL or BigQuery datasets. This lets you run predictive analytics on call durations and peak times without exporting CSV files. The agent uses the Gemini model's long-context window to scan thousands of historical records at once. It identifies patterns in customer behavior and suggests operational tweaks based on actual phone activity.

Automate contact matching using MightyCall MCP Server

By combining Vertex AI with this MCP Server, your agent can cross-reference incoming phone numbers against your enterprise database using `list_contacts`. The agent runs the check to find matches and updates stale directories using `create_contact`. This integration works natively with Google Cloud IAM permissions. You don't need to hardcode API credentials inside your agent definitions to keep your customer directory synchronized.

Route missed calls using Gemini long-context reasoning

When customers leave messages, your Google ADK agent calls `list_voicemails` to gather the audio transcripts and metadata. Gemini processes these transcripts to determine the urgency of each missed call. It then checks `list_business_numbers` to see which department was targeted and routes the follow-up task to the right team. This keeps your response times low without requiring a human to listen to every recording.

Setup guide

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

Use the `McpToolset` class with your Vinkius HTTP endpoint and pass it to your `LlmAgent` tools parameter. This exposes tools like `list_calls` and `list_contacts` directly to your Gemini-powered agent.

Yes, the agent can invoke the `make_call` tool to initiate outbound calls. You can restrict this tool using the `tool_names` filter in your ADK setup if you only want the agent to read data.

Yes, you can pass large lists of call histories from `list_calls` directly into Gemini's massive context window. The agent can analyze hours of phone metadata in a single run.

Use the `tool_names` parameter in the `StreamableHttpServerParameters` config. This lets you block tools like `make_call` while keeping read-only tools like `list_voicemails` active.

Your contact records retrieved via `list_contacts` are transmitted through encrypted HTTPS channels directly to your Google Cloud environment. Vinkius runs the server in an ephemeral sandbox, meaning no contact names or phone numbers are cached on our servers.

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