How to Use the Webhook.site MCP in OpenAI Agents SDK

Q: How do I check webhooks with Webhook.site using the OpenAI Agents SDK?

Simply use getrequests to pull all captured payloads for any token. This shows you the full body and headers of every incoming HTTP request. It's a direct view into what your external services are sending.

Q: Can I create multiple tokens for Webhook.site when using the OpenAI Agents SDK?

Yeah, absolutely. Use createtoken to generate unique URLs for different test scenarios. This keeps your webhooks segregated and makes it easy to track which endpoint caused an issue.

Q: How do I update a token's details with Webhook.site using the OpenAI Agents SDK?

Use updatetoken when you need to change something about an existing credential, like setting new permissions or updating metadata. It lets you maintain your setup without having to delete and recreate everything.

Q: If my agent needs to send a custom response via Webhook.site using the OpenAI Agents SDK, how do I set it?

You use setresponse. This tool lets you manually define the exact JSON or plain text body that the MCP Server will return when a specific request hits your token.

Debug HTTP flows and inspect webhooks with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Webhook.site to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Test incoming payload data

The `get_requests` tool pulls all payloads captured by a specific token. You can see exactly what your external services are sending to your agent, which is huge for debugging. Don't just guess if the webhook fired correctly; inspect it directly. This lets you validate that incoming data matches expectations before your specialized agents run.

Control token functionality

You manage webhooks and credentials using tools like `list_tokens` and `delete_token`. Need a new endpoint? Use `create_token` to get a fresh URL that you can immediately use in your agent setup. If a test fails, or the token gets compromised, these functions let you clean up fast. You're running production code here; cleanup needs to be simple and reliable.

Automate server responses

The `set_response` tool lets you define what your MCP Server sends back to a client during testing. Instead of getting an error, you can force the webhook to receive a clean JSON payload. This is key for simulating successful external API calls right within your agent's test environment. You dictate the outcome.

Setup guide

Set up Webhook.site MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Webhook.site tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Webhook.site tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Webhook.site tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Webhook.site Agent",
            instructions="You have access to Webhook.site tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Simply use `get_requests` to pull all captured payloads for any token. This shows you the full body and headers of every incoming HTTP request. It's a direct view into what your external services are sending.

Yeah, absolutely. Use `create_token` to generate unique URLs for different test scenarios. This keeps your webhooks segregated and makes it easy to track which endpoint caused an issue.

Use `update_token` when you need to change something about an existing credential, like setting new permissions or updating metadata. It lets you maintain your setup without having to delete and recreate everything.

The server handles standard HTTP request payloads, including JSON bodies, headers, and query parameters. You'll be inspecting structured webhooks data.

You use `set_response`. This tool lets you manually define the exact JSON or plain text body that the MCP Server will return when a specific request hits your token.

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