How to Use the MagicDrip MCP in Google ADK

Q: Can the Google ADK handle MagicDrip webhooks through the MCP Server?

The agent can read the active configurations using listconfiguredwebhooks. To actually process incoming webhook payloads, you will need to route them through Cloud Run to trigger the agent.

Connect MagicDrip to Google ADK and let Gemini agents run your LinkedIn outreach straight from BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MagicDrip MCP to Google ADK

Create your Vinkius account to connect MagicDrip 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 MagicDrip with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery meets the MagicDrip MCP Server

Gemini models can hold a million tokens in context. That means you can dump your entire BigQuery lead database into the agent's memory, and it won't forget the details. It maps those internal records directly to the output of `list_outreach_leads`. Instead of running blind, the agent cross-references your enterprise data before calling `add_linkedin_lead`. You get highly targeted campaign additions based on actual customer behavior tracked in Google Cloud, not just basic LinkedIn filters.

Google ADK campaign analysis

You aren't just sending messages here. You are feeding campaign data into Vertex AI for deep analysis. The agent pulls the raw numbers using `get_campaign_performance` and `get_account_outreach_stats`. Gemini takes those stats and looks for patterns across hundreds of campaigns simultaneously. It identifies exactly which messaging sequences generate replies and which ones trigger spam filters, adjusting your strategy on the fly.

Automated profile and quota checks

Setup is dead simple with the MCP toolset. You pass the server parameters to your LLM agent and it immediately knows how to interact with the platform. Before starting a run, the agent verifies the connection using `get_authenticated_user_profile`. It then checks `get_available_slots_quota` to see exactly how many actions it can take today. If the limits are low, the agent prioritizes `send_direct_linkedin_message` for high-value targets over bulk connection requests.

Setup guide

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

Use the tool names filter when configuring the MCP toolset. You can limit the agent to read-only functions like `get_lead_outreach_details` if you don't want it sending invites.

The agent can read the active configurations using `list_configured_webhooks`. To actually process incoming webhook payloads, you will need to route them through Cloud Run to trigger the agent.

It usually means you hit your daily limit. The agent should always run `check_api_health` and check your quota before attempting to dispatch a message.

Yes. You can run the server locally via Stdio for testing, then switch to the streamable HTTP parameters when deploying your agent to Google Cloud.

The connection request logs and message histories pulled via `send_linkedin_invite` pass through a zero-trust architecture. We don't store your Vertex AI prompts or the prospect replies on our infrastructure.

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