How to Use the Webhook.site MCP in Google ADK

Q: How do I check webhooks with Webhook.site using the Google ADK?

Use getrequests to pull all captured payloads from a token. This gives your agent's developers full visibility into the raw HTTP requests and bodies that hit the server.

Q: Can I list available tokens for Webhook.site using the Google ADK?

Yes, you use listtokens to get a view of every token currently set up on your account. This helps manage the scope and boundaries of your testing environment.

Q: If I update a global variable with Webhook.site using the Google ADK, how is it reflected?

The updateglobalvariable tool lets you change the value or definition of an existing variable. This updated state then becomes available for subsequent calls and actions within your agent's workflow.

Q: How do I simulate a successful API call response via Webhook.site using the Google ADK?

You use setresponse. This tool lets you programmatically define the exact body that your agent expects, ensuring the test environment provides clean data for BigQuery or Vertex AI processing.

Debug webhooks and inspect payloads with Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Webhook.site MCP to Google ADK

Create your Vinkius account to connect Webhook.site 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 Webhook.site with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect captured HTTP requests

The `get_requests` tool retrieves all payloads intercepted by a specific token. When building enterprise agents, seeing the raw incoming data is non-negotiable for debugging data flow. You can validate if BigQuery or Vertex AI services are sending the expected format of data before your Gemini model attempts to reason over it.

Manage custom actions and variables

You define reusable logic with `create_action` and manage state with `create_global_variable`. This lets you build complex, multi-step workflows that mimic real production pipelines. These tools let your agent interact with webhooks in a controlled way, making sure the data it receives is structured exactly how your application needs it.

Set dynamic payloads for testing

Need to test an error state? The `set_response` tool lets you force a specific response body back through the webhook. This allows you to simulate failure modes without needing actual external systems. It’s perfect for ensuring your Google ADK agent handles unexpected or malformed API responses gracefully.

Setup guide

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

Use `get_requests` to pull all captured payloads from a token. This gives your agent's developers full visibility into the raw HTTP requests and bodies that hit the server.

Yes, you use `list_tokens` to get a view of every token currently set up on your account. This helps manage the scope and boundaries of your testing environment.

The `update_global_variable` tool lets you change the value or definition of an existing variable. This updated state then becomes available for subsequent calls and actions within your agent's workflow.

The server captures standard HTTP request payloads, including JSON bodies, headers, and query parameters. You are inspecting structured webhooks data.

You use `set_response`. This tool lets you programmatically define the exact body that your agent expects, ensuring the test environment provides clean data for BigQuery or Vertex AI processing.

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