An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Webhook.site to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Inspect incoming payloads and simulate API responses through your agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 17 capabilities

We ship only the actions that matter.

Capability set01 / 05

01-04

4 capabilities in this set.

Part of 17 available through Webhook.site.

  1. 01

    Update global variable

    This capability modifies a global variable to maintain state across your webhook tests.

  2. 02

    Delete global variable

    Use this to remove a specific global variable from your environment.

  3. 03

    Delete requests

    This capability clears out multiple requests associated with a specific token.

  4. 04

    Delete token

    Use this to permanently remove a webhook token.

Capability set02 / 05

05-08

4 capabilities in this set.

Part of 17 available through Webhook.site.

  1. 05

    Execute action

    This capability runs a configured action for a specific incoming request.

  2. 06

    Update action

    Use this to change the parameters of an existing custom action.

  3. 07

    Create action

    This capability sets up a new custom action for a specific token.

  4. 08

    Create global variable

    This capability adds a new global variable to your testing environment.

Capability set03 / 05

09-11

3 capabilities in this set.

Part of 17 available through Webhook.site.

  1. 09

    Create token

    Use this to generate a new Webhook.site token and URL.

  2. 10

    Delete action

    Use this to remove a custom action from a token.

  3. 11

    Get requests

    This capability retrieves the list of requests captured by a specific token.

Capability set04 / 05

12-14

3 capabilities in this set.

Part of 17 available through Webhook.site.

  1. 12

    Get token

    Use this to pull detailed information about a specific token.

  2. 13

    List actions

    This capability shows all custom actions currently configured for a token.

  3. 14

    List global variables

    Use this to see all global variables currently in use.

Capability set05 / 05

15-17

3 capabilities in this set.

Part of 17 available through Webhook.site.

  1. 15

    List tokens

    This capability provides a list of all your Webhook.site tokens.

  2. 16

    Set response

    Use this to define a dynamic HTTP response for a specific request.

  3. 17

    Update token

    This capability allows you to modify the settings of an existing token.

Real work

What teams actually run

01

Webhook Debugging

Test if your application is correctly receiving and parsing callbacks from third-party services.

02

API Response Mocking

Simulate how your code handles 404, 500, or 201 status codes by setting dynamic responses.

03

Integration Validation

Verify that your system correctly processes incoming data by inspecting the captured payloads.

04

Automated Testing Pipelines

Use configured actions to trigger specific workflows whenever a webhook is received.

Automate a task

Put Webhook.site to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Webhook.site works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Webhook.site to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1120ms average. Fast in production.

Webhook.site is checked daily against the live service.

Daily averagePeak 1386ms
Oct 3Today
Fastest day
870ms
Slowest day
1386ms
14-day trend
Improving-6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 17 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Webhook.site, so you can see the experience inside your AI.

It does not authenticate your account with Webhook.site. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Webhook.site Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_4UGcdultUkkqhC6PeYxs6JG990XLacW5YNGNQO5y/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Webhook.site capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "webhooksite-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_4UGcdultUkkqhC6PeYxs6JG990XLacW5YNGNQO5y/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Webhook.site in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Webhook.site owners hand off.

This MCP is built for developers and engineers who need to test webhooks without the overhead of local infrastructure.

  • 01

    Backend Developers

    They use the agent to test webhooks without setting up local tunnels or public servers.

  • 02

    QA Engineers

    They hand off the task of validating third-party callbacks and simulating API response scenarios to the agent.

  • 03

    DevOps Teams

    They use the agent to monitor incoming alerts and trigger automated responses.

FAQ

Questions Webhook.site owners ask.

  • 01

    How do I use this MCP with my AI client?

    You connect to the MCP via Vinkius and then use your preferred client like Claude or Cursor. Once connected, you just talk to your agent to manage your webhooks.

  • 02

    Do I need to set up a local server to test webhooks?

    No. This MCP allows you to create unique webhook URLs that capture traffic instantly, removing the need for local tunnels.

  • 03

    Can I simulate specific HTTP error codes?

    Yes. You can use the agent to set custom HTTP status codes and body content for specific requests to see how your application reacts.

  • 04

    What information can I see in a captured request?

    You can inspect detailed metadata including headers, query parameters, and the raw payload of any incoming request.

  • 05

    Is my API key stored securely?

    Yes, Vinkius manages your credentials and keeps them secure so you can connect your client once and start working.

  • 06

    How can I create a temporary webhook URL that expires after one hour?

    Use the create_token capability and set the expiry parameter to 3600 seconds. You can also add an alias to make the URL easier to identify.

  • 07

    Can I see the headers and body of the requests sent to my webhook?

    Yes! Use the get_requests capability with your Token ID. It will return a list of captured requests including full headers, query strings, and the raw payload content.

  • 08

    Is it possible to make the webhook return a specific JSON response?

    Absolutely. Use the set_response capability to define a custom content (base64 encoded), status code, and JSON headers for any specific request received by your token.

Explore

More in Developer Tools

Suggestions

Connect Webhook.site to Claude, Cursor, ChatGPT & more