How to Use the NeverBounce MCP in Google ADK

Q: How do I initialize the NeverBounce MCP Server inside Google ADK?

Install the framework and configure an McpToolset with your Vinkius URL. Pass that toolset into the LlmAgent constructor under the tools parameter.

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

Yes. You use the toolnames argument to restrict access. This lets you hide deletion capabilities while allowing status checks.

Q: How do I check the status of a NeverBounce job with Google ADK?

Your agent calls the getjobstatus tool. You set up a loop in your Python code that waits for a completion signal before proceeding.

Connect the NeverBounce MCP Server to Google ADK to scrub BigQuery contact lists using Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NeverBounce MCP to Google ADK

Create your Vinkius account to connect NeverBounce 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 NeverBounce with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scrub massive lists with Gemini

`create_job_from_input` takes raw text blocks and turns them into bulk verification tasks. When your agent pulls thousands of rows from BigQuery, Gemini's large token context window digests the entire dataset and passes it directly to this tool. After submission, the agent triggers `parse_job` and `start_job` to begin the actual scrubbing process. You integrate this straight into your Vertex AI pipelines. It cleans up enterprise data lakes before feeding them into marketing campaigns.

Single address checks via MCP Server

`check_email` verifies individual contacts on the fly. If an agent reads a long-form document or scrapes a website, it extracts the addresses and validates them instantly. This stops bad data from entering your Google Cloud infrastructure. The agent filters out the dead inboxes and only writes the valid ones back to your database.

Autonomous job monitoring

`list_jobs` and `get_job_status` give your Gemini models full visibility into the verification queue. The agent polls these endpoints using the HTTP transport layer built into the framework. When the status shows complete, `get_job_results` retrieves the clean data. You restrict which of these operations are exposed using the `tool_names` filter in your configuration.

Setup guide

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

Install the framework and configure an `McpToolset` with your Vinkius URL. Pass that toolset into the `LlmAgent` constructor under the `tools` parameter.

Yes. You use the `tool_names` argument to restrict access. This lets you hide deletion capabilities while allowing status checks.

It pairs perfectly. The model holds massive lists of unverified contacts in memory and feeds them into the bulk creation tools without losing track of the data.

Your agent calls the `get_job_status` tool. You set up a loop in your Python code that waits for a completion signal before proceeding.

The server routes your raw contact strings through a secure, ephemeral V8 isolate. Vinkius requires just one endpoint token to handle auth, and we never write your leads to disk.

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