How to Use the Thoughtly MCP in Google ADK

Q: How do I set up the Thoughtly MCP Server with the Google ADK?

You'll use the McpToolset from the Google ADK library, pointing it to your Vinkius server URL. Pass that toolset to your LlmAgent and it will automatically discover all the Thoughtly tools.

Q: Can I restrict which Thoughtly tools my Google ADK agent can use?

Yes, the McpToolset constructor in the Google ADK has a toolnames filter. You can provide a specific list of tool names, like 'triggercall', 'listcontacts', to create a specialized agent with limited permissions.

Integrate Thoughtly's voice AI with your Google Cloud data using the Google ADK. Enterprise-grade agents, now with a voice.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Thoughtly MCP to Google ADK

Create your Vinkius account to connect Thoughtly to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Thoughtly with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build a Voice-Enabled CRM on GCP

Connect your agent directly to a contact database. Your Gemini-powered agent can use `create_contact` to onboard a new user or `list_contacts` to get a full picture of your customer base. It's the simplest way to give your cloud infrastructure a voice. Keep that data clean. Your agent can run `update_contact` to fix a typo in a record or `delete_contact` to remove old entries. If it needs to check one person's details, it uses `get_contact`.

Automate Outreach and Reporting

The main event: your agent can make phone calls. Use `trigger_call` to have your agent start a conversation, like a follow-up or a qualification screen. This isn't just scheduling tasks; it's executing them. All activity is logged. Your agent can pull a complete log with `list_calls`, then grab the transcript from a specific conversation using `get_call_history`. You can pipe this data directly into BigQuery for analysis.

Manage Agent Personas in Google Cloud

Give your agent context about its own capabilities. It can call `get_user` to see its own profile and permissions within the Thoughtly system. This is key for logging and multi-agent setups. You're not stuck with one voice. The `list_interviews` tool lets your agent see all available voice agent configurations. It can then use `get_interview` to inspect a specific persona's details before making a call. This MCP Server gives you real control.

Setup guide

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

You'll use the `McpToolset` from the Google ADK library, pointing it to your Vinkius server URL. Pass that toolset to your `LlmAgent` and it will automatically discover all the Thoughtly tools.

Yes. You can build an agent that reads contact info from BigQuery or another GCP service, then uses Thoughtly's tools to initiate the outreach. The Google ADK is built to connect these different services.

It's a perfect match. Your agent can hold a massive amount of context from your internal documents, then use that information to have a relevant conversation via a call from your Thoughtly MCP server.

Yes, the `McpToolset` constructor in the Google ADK has a `tool_names` filter. You can provide a specific list of tool names, like `['trigger_call', 'list_contacts']`, to create a specialized agent with limited permissions.

The Thoughtly server only handles the specific contact info and call transcripts needed for an operation. Vinkius isolates every MCP Server request in a disposable V8 sandbox. Nothing is stored long-term on the server, and all access is gated by your private token.

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