How to Use the Clearout MCP in Google ADK

Q: How does Clearout integration with Google ADK help manage costs?

Your agent can call the getcredits tool before starting a large job. This lets you programmatically check if you have enough credits, preventing failed runs and integrating cost controls directly into your workflow.

Q: What's the difference between verifyemail and verifycatchall?

The verifyemail tool is your standard check for any single email. You'd use verifycatchall for a more specific test on emails from domains that are configured to accept all incoming mail, which can be a higher risk for deliverability.

Clean your marketing lists in BigQuery using Google ADK and Clearout.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clearout MCP to Google ADK

Create your Vinkius account to connect Clearout 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 Clearout with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify Lists Straight From BigQuery

Your Gemini agent can now run your list cleaning for you. Have it query an email list from a BigQuery table, then pass the entire batch to the `verify_bulk` tool. Clearout handles the verification process in the background. Once the job is complete, the agent can use `get_bulk_status` to confirm it's done, then `download_results` to fetch the clean data. From there, it can write the results directly into a new BigQuery table, completing the entire workflow without manual intervention.

Let Gemini Agents Find and Vet Prospects

This is where Gemini's long-context window shines. Your agent can read an entire market analysis report or a long company transcript. From that context, it can identify key people and then use the `find_email` tool to locate their business email address. Immediately after finding the email, the same agent can use `verify_email` to check if it's deliverable. This turns a research and data entry task into a single, autonomous operation that feeds your CRM with vetted contacts.

Run Enterprise Jobs with this MCP Server

Integrate email verification into your scheduled Google Cloud workflows. You can have a Cloud Scheduler function trigger an agent that first calls `check_clearout_status`. If the API is healthy, it proceeds with a large verification job. For cost control, the agent can call `get_credits` before starting. If the balance is below a certain threshold, it can publish a message to a Pub/Sub topic to alert your team. This MCP Server provides the necessary signals to build resilient, enterprise-grade automations on Google Cloud.

Setup guide

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

Your agent can query the emails from a BigQuery table, send them to the `verify_bulk` tool, and then use `download_results` to get the clean list. Finally, it can write those results back to a new table in BigQuery.

Yes. With Gemini's large context window, your agent can read the document to identify prospects. Then it can use the `find_email` and `verify_email` tools to get and validate their contact information.

Your agent can call the `get_credits` tool before starting a large job. This lets you programmatically check if you have enough credits, preventing failed runs and integrating cost controls directly into your workflow.

The `verify_email` tool is your standard check for any single email. You'd use `verify_catchall` for a more specific test on emails from domains that are configured to accept all incoming mail, which can be a higher risk for deliverability.

Yes, it is. The server only sees the email addresses during the verification process. It runs in a zero-trust Vinkius environment, completely isolated from your Google Cloud projects, and doesn't store your data after the job is done.

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