How to Use the CoderPad MCP in Google ADK

Q: Can Google ADK agents read my CoderPad session history?

Yes, the agent uses listcoderpadsessions and getpadsessiondetails to retrieve comprehensive interview data. It then processes this information using the Gemini model's reasoning capabilities.

Connect CoderPad to your Google ADK infrastructure for data-driven hiring.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CoderPad MCP to Google ADK

Create your Vinkius account to connect CoderPad 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 CoderPad with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync CoderPad with Google ADK workflows

The `list_coderpad_sessions` tool pulls your active technical interviews directly into your agent's memory. It allows your model to reason about current coding tasks alongside your BigQuery data. Use `get_my_coderpad_profile` to verify the active interviewer's credentials before allowing the agent to perform sensitive actions. It ensures only authorized users manage your cloud-hosted interviews.

Analyze interview logs at scale

Feed the output of `get_pad_event_log` into your Gemini context window to summarize candidate performance. You can process long-form coding histories without hitting token limits. Calling `get_pad_session_details` provides the exact code state needed for your agent to suggest improvements or feedback. It makes auditing large batches of interviews much faster.

Query your interview question bank

Your agent uses `list_coderpad_questions` to search your internal library for the most relevant tasks. It connects your hiring criteria to the specific candidate's skill set. `list_coderpad_org_users` helps your agent identify the right interviewer to tag for a review. It keeps your organization's hiring loop tight and fully synced with your Google Cloud environment.

Setup guide

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

Define an McpToolset using your Vinkius server URL and include it in your LlmAgent tool list. This allows your agent to call CoderPad functions natively.

Yes, the agent uses `list_coderpad_sessions` and `get_pad_session_details` to retrieve comprehensive interview data. It then processes this information using the Gemini model's reasoning capabilities.

The server supports Stdio and HTTP transports, making it simple to run within your existing Google Cloud infrastructure. It functions as a standard MCP Server for your agent.

You provide a single endpoint token via the Vinkius platform. The server handles the handshake, so your agent only sees the authorized tools.

We enforce strict transport security for every request involving your interview pads. Data is ephemeral, and the server operates within an isolated V8 sandbox to prevent unauthorized access to your candidate logs.

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