How to Use the CallFire MCP in Google ADK

Q: How do I configure CallFire with Google ADK?

Initialize an McpToolset using your Vinkius endpoint URL. Pass that toolset into the tools array of your LlmAgent. The Gemini model will immediately see all available communication functions.

Q: Can Google ADK restrict which CallFire tools the agent uses?

You can filter the exposed functions using the toolnames parameter. If you only want an agent reading data, just allow getaccountinfo and listcalls while blocking the send commands.

Q: What transport layers does this integration support?

The integration works over HTTP transport. You configure StreamableHttpServerParameters with your Vinkius URL to establish the connection.

Connect CallFire to Google ADK to trigger voice and SMS campaigns directly from your Gemini enterprise agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallFire MCP to Google ADK

Create your Vinkius account to connect CallFire 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 CallFire with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CallFire MCP Server for Gemini

The `send_sms` and `send_voice_call` tools change how you handle bulk communications with Gemini's massive context window. You dump thousands of customer records from BigQuery straight into the agent's context. The agent parses the data and contacts exactly the right people. Middleware is no longer necessary to sync databases with your dialer. The agent reads the raw data, decides who needs a message, and executes the tools. You just pass the `McpToolset` to your `LlmAgent` and let Google Cloud infrastructure handle the scaling.

Deep Campaign Analytics

The agent calls `list_calls` and `list_sent_sms` to pull historical delivery data into Vertex AI. It analyzes these logs against your enterprise datasets to figure out why certain regions have lower pickup rates. Granular inspection happens automatically. When the agent spots an anomaly, it hits `get_call_details` or `get_sms_details` for the specific transaction. It reads the error codes and adjusts the next batch of messages on the fly.

Asset and Webhook Audits

Your Google ADK setup can run daily audits using `list_keywords` to check active short codes. It verifies your audio library with `list_campaign_sounds` before launching a voice broadcast. System health checks take seconds. The agent monitors `get_account_info` for billing status and pulls `list_webhooks` to ensure your external callbacks are still firing. You catch configuration drift before a major campaign goes live.

Setup guide

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

Initialize an `McpToolset` using your Vinkius endpoint URL. Pass that toolset into the `tools` array of your `LlmAgent`. The Gemini model will immediately see all available communication functions.

You can filter the exposed functions using the `tool_names` parameter. If you only want an agent reading data, just allow `get_account_info` and `list_calls` while blocking the send commands.

Your agent can hold both BigQuery and CallFire MCP toolsets simultaneously. It queries your database for target users, then loops through the results to trigger `send_sms` for each row.

The integration works over HTTP transport. You configure `StreamableHttpServerParameters` with your Vinkius URL to establish the connection.

We run your CallFire MCP instance in a zero-trust V8 isolate. SMS message bodies and recipient phone numbers pass through temporary memory and are never written to disk. Authentication is handled entirely by the Vinkius gateway.

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