How to Use the Dexatel MCP in Google ADK

Q: How do I connect Dexatel to Google ADK?

Install google-adk via pip. Wrap your endpoint in McpToolset using StreamableHttpServerParameters, then pass that into your LlmAgent tools array.

Q: Does Google ADK support filtering the Dexatel tools?

It does. Use the toolnames filter in your configuration to expose only specific endpoints, like restricting an agent to just reading templates.

Q: How do agents enforce compliance?

They query listsmstemplates. The agent fetches pre-approved text structures and populates the variables, preventing it from generating non-compliant messages on the fly.

Q: Are my customer phone numbers safe?

When the agent pulls data via getcontactprofile, the phone numbers and history route through an ephemeral Vinkius sandbox. Authentication requires just one endpoint token, and the managed MCP Server shuts down the moment the task finishes.

Hook the Dexatel MCP Server into Google ADK to let your Gemini agents read BigQuery data and trigger text message campaigns.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dexatel MCP to Google ADK

Create your Vinkius account to connect Dexatel 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 Dexatel with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute SMS campaigns via this MCP Server

The `send_sms_message` tool pushes text messages to any phone number. Write a pipeline where the agent pulls a customer segment from BigQuery, formats the data, and fires the texts. It checks `get_account_balance_metadata` first so you avoid running dry mid-campaign. Large enterprise workloads require strict sender rules. Your agent queries `list_authorized_sender_ids` to match specific regional virtual numbers with the right customer cohorts. Gemini's massive context window processes the entire list of IDs and customer records in a single pass.

Analyze messaging history at scale

The `list_sms_messages` tool returns your entire sent and received text history. Feed this directly into your agent's context. Gemini reads thousands of past messages at once, categorizing user sentiment or identifying common support questions without breaking a sweat. When you need to find something specific, the agent uses `search_sms_by_content`. It hunts down keywords or phone numbers across the database. If a delivery goes wrong, `get_sms_message_details` pulls the raw metadata so your agent diagnoses the carrier rejection.

Sync contacts and track failures

The `list_messaging_contacts` tool retrieves every entry in your address book. Your agent pulls this list and cross-references it with your Google Cloud CRM data. If it spots a discrepancy, it uses `get_contact_profile` to grab the full interaction history for that specific user. Carriers drop messages. Your agent calls `list_failed_sms_deliveries` to identify which numbers bounced. Instruct the agent to automatically flag these failed numbers in your database so you stop wasting money texting dead lines.

Setup guide

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

Install `google-adk` via pip. Wrap your endpoint in `McpToolset` using `StreamableHttpServerParameters`, then pass that into your `LlmAgent` tools array.

Yes. Gemini's 1M+ token context window easily swallows the output from `list_sms_messages`, letting the agent analyze your entire communication log at once.

It does. Use the `tool_names` filter in your configuration to expose only specific endpoints, like restricting an agent to just reading templates.

They query `list_sms_templates`. The agent fetches pre-approved text structures and populates the variables, preventing it from generating non-compliant messages on the fly.

When the agent pulls data via `get_contact_profile`, the phone numbers and history route through an ephemeral Vinkius sandbox. Authentication requires just one endpoint token, and the managed MCP Server shuts down the moment the task finishes.

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