How to Use the CallRail MCP in Google ADK

Q: How can my Google ADK agent use CallRail tools?

Install google-adk and create an McpToolset that points to your Vinkius server URL for this MCP server. You pass that toolset into your LlmAgent, and your Gemini agent can start calling CallRail functions.

Q: Can I use this to get CallRail data into Google Sheets?

Yes. Your Google ADK agent can fetch data using tools like listcalls, and then use a separate toolset for Google Sheets to write the data into a spreadsheet. It's a common pattern for building automated reports.

Q: How do I filter the calls my Google ADK agent gets from CallRail?

The listcalls tool accepts parameters like date ranges. Your agent can specify these when it calls the tool to narrow down the results to a specific day, week, or month you want to analyze.

Connect Google ADK agents to your CallRail data for analysis inside Google Cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallRail MCP to Google ADK

Create your Vinkius account to connect CallRail 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 CallRail with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe CallRail data directly into BigQuery

This is the most direct way to get your marketing data into Google Cloud for analysis. Your Gemini-powered agent can use `list_calls` and `list_form_submissions` to fetch raw performance data straight from CallRail's API. Once the agent has the data, it can pipe it right into a BigQuery table. This is perfect for building long-term analytics dashboards, tracking marketing attribution over time, or feeding data into a Vertex AI model. The whole process can be automated by your agent.

Manage your CallRail account at enterprise scale

Build internal tools for managing a large CallRail organization. A Google ADK agent can get a high-level view with `list_companies` and `list_users`, giving you a starting point for audits or reporting. From there, the agent can iterate through the list and use `get_company_details` to check configurations or pull specific data for each sub-account. It's a solid way to automate tedious admin work, all from within your existing Google Cloud environment.

Use Gemini's long context to analyze call trends

The Google ADK shines when you give it a lot of data. You can feed a Gemini agent the full output from tools like `list_calls` and `list_tags` for an entire quarter, and it won't lose context. This lets you ask complex questions that require cross-referencing lots of information. For example, your agent could find correlations between call volume and specific tags, or identify which marketing sources from `list_trackers` generate the longest phone calls. This MCP Server makes the raw data available for that kind of deep analysis.

Setup guide

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

Install `google-adk` and create an `McpToolset` that points to your Vinkius server URL for this MCP server. You pass that toolset into your `LlmAgent`, and your Gemini agent can start calling CallRail functions.

Yes. Your Google ADK agent can fetch data using tools like `list_calls`, and then use a separate toolset for Google Sheets to write the data into a spreadsheet. It's a common pattern for building automated reports.

The `list_calls` tool accepts parameters like date ranges. Your agent can specify these when it calls the tool to narrow down the results to a specific day, week, or month you want to analyze.

This server doesn't access call transcripts directly. It provides metadata like call duration, source, and tags. You can use an agent to pull a list of calls with `list_calls` and then use another service to handle the transcription and analysis.

Yes. The server acts as a secure proxy. It relays requests for call details and form submissions from your Google ADK agent to CallRail's API and sends the response back. The data is encrypted in transit and never stored on the Vinkius MCP Server.

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