How to Use the Deep Talk MCP in Google ADK

Q: How do I configure Deep Talk with Google ADK?

Install google-adk using pip. Initialize an MCP Toolset with StreamableHttpServerParameters pointing to the Vinkius URL. Pass this toolset to your LlmAgent configuration.

Q: Can Google ADK read Deep Talk sentiment scores?

The agent executes getsentimentanalytics to pull the distribution of positive and negative scores. It then uses Gemini's long context to reason about the dataset as a whole.

Q: How does the agent know which NLP models to use?

It runs listavailablenlpmodels to see the current options. The response includes clusterers and sentiment analyzers ready for deployment on your datasets.

Q: Can I restrict which Deep Talk tools the Google ADK agent sees?

You pass a specific array to the toolnames filter during setup. This limits the agent to only the exact operations you want it to perform.

Feed Deep Talk MCP Server conversation clusters and sentiment scores straight into your Google ADK 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 Deep Talk MCP to Google ADK

Create your Vinkius account to connect Deep Talk 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 Deep Talk with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze support clusters with Gemini

Your agent uses `list_conversation_clusters` and `list_extracted_topics` to pull semantically similar support tickets into its context window. Gemini holds over a million tokens, so you dump entire topic distributions in a single prompt. It reads the representative keywords and cluster sizes. The system then cross-references those themes with your existing BigQuery tables to find correlations between support complaints and user retention.

Track Deep Talk ingestion pipelines

Executing `list_connected_sources` and `list_processing_tasks` lets your Google Cloud infrastructure monitor incoming support data. The agent checks synchronization status across external platforms before triggering downstream Vertex AI pipelines. We expose completion percentages for every active job. You write the logic that tells the agent to wait until ingestion hits completion before it starts applying NLP categorizers.

Google ADK MCP Server integration

The `get_sentiment_analytics` and `get_dataset_metadata` tools feed dataset creation dates and negative sentiment ratios directly to your LlmAgent. The MCP Toolset handles the HTTP transport automatically. You filter exposed tools using the optional `tool_names` parameter. If a specific agent only needs to read sentiment, you restrict it from seeing the account billing details or external source lists.

Setup guide

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

Install `google-adk` using pip. Initialize an MCP Toolset with `StreamableHttpServerParameters` pointing to the Vinkius URL. Pass this toolset to your `LlmAgent` configuration.

The agent executes `get_sentiment_analytics` to pull the distribution of positive and negative scores. It then uses Gemini's long context to reason about the dataset as a whole.

It runs `list_available_nlp_models` to see the current options. The response includes clusterers and sentiment analyzers ready for deployment on your datasets.

You pass a specific array to the `tool_names` filter during setup. This limits the agent to only the exact operations you want it to perform.

Customer support transcripts route through a strict zero-trust environment. Vinkius executes the requests inside a V8 Isolate Sandbox that destroys itself after the transaction 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