How to Use the Webhook.site MCP in Pydantic AI

Q: How do I check webhooks with Webhook.site using Pydantic AI?

Use getrequests to pull all captured payloads for a token. Since you care about data correctness, this allows you to manually verify that the incoming fields match your expected Python types.

Q: Can I list available tokens for Webhook.site using Pydantic AI?

Yes, run listtokens to get an inventory of all endpoints. This helps you keep track of every credential attached to your type-safe agent system.

Q: If I update a custom action with Webhook.site using Pydantic AI, what happens?

The updateaction tool lets you modify the underlying logic or parameters of an existing webhook behavior. This is useful if you need to adjust how your agent handles certain input scenarios.

Q: How do I simulate a clean response via Webhook.site using Pydantic AI?

You use setresponse. This tool lets you define the exact JSON structure and type of data that should be returned, ensuring it validates perfectly against your Pydantic models.

Validate and debug webhooks with Pydantic AI's type-safe MCP Server.

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 Pydantic AI

Create your Vinkius account to connect Webhook.site to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect incoming request data

The `get_requests` tool retrieves payloads captured by a specific token. Because your agent relies on strict typing, inspecting the raw input is critical for preemptive validation. This lets you confirm that external systems are sending fields and types that match your Pydantic models before any processing happens.

Manage tokens and credentials

You control webhooks using `list_tokens` to see all active endpoints. If a test fails, you can use `delete_token` to eliminate the bad URL entirely, keeping your environment clean. Managing these resources with tools like `create_token` ensures every endpoint used by your agent is tracked and accounted for.

Control dynamic webhook responses

The `set_response` tool lets you define a predictable output payload. You can force the webhook to return data that perfectly matches your Pydantic schema, guaranteeing type safety during testing. This ability to simulate perfect input is crucial; it proves your agent logic works even if the real external API is flaky.

Setup guide

Set up Webhook.site MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "webhooksite-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Webhook.site tools.",
)

result = await agent.run("List recent Webhook.site transactions")
print(result.output)

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 Pydantic AI

Use `get_requests` to pull all captured payloads for a token. Since you care about data correctness, this allows you to manually verify that the incoming fields match your expected Python types.

Yes, run `list_tokens` to get an inventory of all endpoints. This helps you keep track of every credential attached to your type-safe agent system.

The `update_action` tool lets you modify the underlying logic or parameters of an existing webhook behavior. This is useful if you need to adjust how your agent handles certain input scenarios.

The server captures standard HTTP request payloads, including JSON bodies, headers, and query parameters. You're inspecting structured webhooks data that your agent will validate.

You use `set_response`. This tool lets you define the exact JSON structure and type of data that should be returned, ensuring it validates perfectly against your Pydantic models.

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