How to Use the Hookdeck MCP in Google ADK

Q: How do I initialize the Hookdeck MCP in Google ADK?

Install the google-adk package. Define a McpToolset using your HTTP endpoint parameters, then pass it to your LlmAgent under the tools array.

Q: Can Google ADK filter which Hookdeck tools the agent accesses?

Yes. You can use the toolnames filter in your McpToolset configuration. This restricts the agent to safe read-only commands like countconnections or listsources.

Q: Can the Google ADK agent test payload mutations?

It runs testtransformation to validate JavaScript modifications against actual webhook data. The agent verifies the output before committing the change with updatetransformation.

Connect the Hookdeck MCP Server to the Google ADK to let Gemini agents manage webhooks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hookdeck MCP to Google ADK

Create your Vinkius account to connect Hookdeck 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 Hookdeck with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Hookdeck MCP Server Metrics Analysis

Gemini agents pull queue statistics via `get_metrics_queue_depth` and `get_metrics_events`. They can cross-reference these delivery metrics with your existing Google Cloud infrastructure logs. Long-context reasoning allows the agent to analyze weeks of event data in a single prompt. You can pipe this data directly into BigQuery for long-term storage. When an anomaly occurs, the agent queries `list_attempts` to find the exact failure points and correlates them with Vertex AI anomaly detection models.

Intelligent Connection Management

Your agent uses `create_source` and `create_destination` to spin up new routing paths on demand through this MCP integration. If a third-party API changes its rate limits, the agent adjusts your settings using `update_destination`. Manual dashboard configuration becomes obsolete. The agent reads the current state with `list_connections`, determines the optimal routing strategy, and applies the changes instantly via `upsert_connection`.

Automated Event Replays

When your Google ADK agent detects a 500 error from an external service, it immediately calls `pause_connection`. This halts the queue while the agent investigates the root cause. Once the external service recovers, the agent executes `unpause_connection`. It then iterates through the failed requests and triggers `retry_request` to process the backlog without dropping a single payload.

Setup guide

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

Install the `google-adk` package. Define a `McpToolset` using your HTTP endpoint parameters, then pass it to your `LlmAgent` under the `tools` array.

Yes. You can use the `tool_names` filter in your `McpToolset` configuration. This restricts the agent to safe read-only commands like `count_connections` or `list_sources`.

Gemini's massive context window processes hundreds of webhook payloads simultaneously. The agent fetches logs via `list_events` and identifies structural patterns in the failed requests.

It runs `test_transformation` to validate JavaScript modifications against actual webhook data. The agent verifies the output before committing the change with `update_transformation`.

The tools access raw HTTP request headers and JSON bodies via endpoints like `get_request`. Vinkius handles authentication ephemerally, meaning your workspace tokens are never exposed to the LLM provider's training data.

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