How to Use the JustCall MCP in Google ADK

Q: How do I initialize JustCall inside Google ADK?

Install the google-adk package. Set up McpToolset with your Vinkius URL using StreamableHttpServerParameters. Pass that toolset to your LlmAgent.

Q: Can Google ADK filter which JustCall MCP tools the agent sees?

You use the toolnames parameter in the McpToolset configuration. This lets you expose listcalls while hiding sendmessage if you want a read-only agent.

Q: How does the agent handle large JustCall call histories?

Gemini eats the massive context. You just call listcalls repeatedly and feed the JSON straight into the prompt. The model processes the entire timeline at once.

Connect the JustCall MCP Server to Google ADK to let your Gemini agents act on massive call logs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JustCall MCP to Google ADK

Create your Vinkius account to connect JustCall 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 JustCall with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Contextualize millions of tokens

Your Google ADK agent pulls massive text histories using `list_messages` and `get_message_details`. Because Gemini handles over a million tokens, you can dump an entire year of SMS interactions into the context window. The agent spots trends across thousands of messages without chunking the data. You tie this directly into BigQuery. The agent reads a customer ID from your database, grabs the matching phone records via `list_calls`, and writes a summary back to Vertex AI. You stop building custom ETL pipelines for simple text analysis.

Google ADK outbound SMS triggers

The `send_message` tool fires SMS texts straight from your Google Cloud infrastructure. When a BigQuery alert triggers, your agent formats an alert and pushes it through the JustCall MCP Server. You get instant mobile notifications tied to your enterprise data. You control exactly which numbers send these alerts. The agent checks `list_account_numbers` to find the correct regional line before dispatching the text. It keeps your outbound communication organized by department.

Sync contacts across Google Cloud

Your agent keeps your CRM data fresh using `create_contact` and `get_contact`. When a new lead drops into your Vertex AI pipeline, the agent pushes that profile straight into JustCall. Your sales team sees the new number ring immediately. Managing the team structure works the same way. The agent lists active agents via `list_team_users` and checks `list_webhooks` to ensure routing rules match your current roster. You handle telephony configuration through code.

Setup guide

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

Install the `google-adk` package. Set up `McpToolset` with your Vinkius URL using `StreamableHttpServerParameters`. Pass that toolset to your `LlmAgent`.

You use the `tool_names` parameter in the `McpToolset` configuration. This lets you expose `list_calls` while hiding `send_message` if you want a read-only agent.

Gemini eats the massive context. You just call `list_calls` repeatedly and feed the JSON straight into the prompt. The model processes the entire timeline at once.

You connect via HTTP transport. The Vinkius endpoint provides a secure, stateless connection that integrates perfectly with Google Cloud's serverless architecture.

The server runs in a zero-trust V8 Isolate. When your agent requests sensitive PII via `get_contact`, the request routes securely without persisting on Vinkius infrastructure. The ephemeral instance guarantees your phone numbers and names stay private.

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