How to Use the Apideck MCP in Google ADK

Q: How do I set up Apideck with the Google ADK in Python?

Install the package using pip install google-adk first. Then, define your toolset using McpToolset with your Vinkius HTTP URL and pass it to your LlmAgent instance.

Q: Can I limit which Apideck tools my Google ADK agent can access?

Yes, you can restrict access. Use the toolnames filter when initializing your McpToolset to expose only specific tools like listcrmcontacts.

Q: How can I use this toolset alongside BigQuery data?

Your agent can fetch raw CRM records using listcrmcontacts and pass that data directly to BigQuery using your Google ADK cloud tools. This lets you enrich your data warehouse with live integration data.

Feed live CRM data and unified API responses directly 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 Apideck MCP to Google ADK

Create your Vinkius account to connect Apideck 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 Apideck with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject CRM contacts into Gemini's long context window

The `list_crm_contacts` tool pulls customer data from your connected CRMs directly into your Google ADK workflows. Gemini models use this fresh data to analyze pipeline health or draft personalized responses based on real-time contact history. Because Gemini handles up to one million tokens, you can feed entire contact lists into the prompt context. This MCP Server integration bypasses the need for complex ETL pipelines, keeping your data fresh and accessible.

Configure Vault connections on Google Cloud

The `list_vault_connections` and `get_vault_connection` tools query active user integrations from your Google ADK agent. This lets your enterprise systems monitor which third-party apps are linked to your accounts. When an integration needs to be removed, the agent calls `delete_vault_connection` to revoke access instantly. Security teams can audit these actions through standard Google Cloud logging tools.

Route raw requests through the Apideck MCP Server

The `execute_proxy` tool routes custom API requests to any connected platform through a single endpoint. Your agent uses this tool to access specialized downstream endpoints that aren't covered by default schemas. By pairing this with `create_vault_session`, your Google ADK agent initiates new authentication flows for users. The entire lifecycle happens inside a secure, ephemeral V8 sandbox hosted by Vinkius.

Setup guide

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

Install the package using `pip install google-adk` first. Then, define your toolset using `McpToolset` with your Vinkius HTTP URL and pass it to your `LlmAgent` instance.

Yes, you can restrict access. Use the `tool_names` filter when initializing your `McpToolset` to expose only specific tools like `list_crm_contacts`.

It supports both Stdio and HTTP transports. For hosted Vinkius MCP deployments, you will use the streamable HTTP server parameters to connect your agent.

Your agent can fetch raw CRM records using `list_crm_contacts` and pass that data directly to BigQuery using your Google ADK cloud tools. This lets you enrich your data warehouse with live integration data.

Your contact records and proxy payloads exist only in memory during the execution of the agent run. Vinkius runs every MCP request in an isolated, ephemeral V8 sandbox that deletes all data as soon as the connection closes.

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