How to Use the Hookdeck (Webhook Gateway) MCP in Claude Code

Q: How do I add the Hookdeck (Webhook Gateway) MCP server to Claude Code?

It's a single command. Run claude mcp add --transport http hookdeck -- . Then verify it's connected with claude mcp list. The configuration is saved to your /.claude.json file.

Q: What's a good way to monitor Hookdeck connection counts with Claude Code?

For a simple check, just run claude mcp exec hookdeck countconnections. You can add this to a monitoring script and compare the output over time to detect unexpected changes in your infrastructure.

Q: How do I handle a large batch of failed webhooks from the terminal with Hookdeck (Webhook Gateway) and Claude Code?

First, find the problem using claude mcp exec hookdeck listissues. Then, use the query from the issue to run claude mcp exec hookdeck bulkretryevents --query '...'. It's a two-command fix for potentially thousands of failed events.

Manage Hookdeck from your terminal. Perfect for CI/CD pipelines, cron jobs, and shell scripts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hookdeck (Webhook Gateway) MCP to Claude Code

Create your Vinkius account to connect Hookdeck (Webhook Gateway) to Claude Code 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 (Webhook Gateway) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script Your Entire Webhook Infrastructure

Use tools like `create_source`, `create_destination`, and `create_connection` directly in your shell scripts. Claude Code lets you pipe these commands together to provision and configure your entire webhook routing setup from a single bash file. This is how you automate your environments for real. A single script can check if a connection exists with `claude mcp exec hookdeck list_connections`, and if not, create it. It's declarative infrastructure, but from the command line you already live in.

Headless Monitoring and Alerting

The `get_metrics_queue_depth` tool is built for automation. Run `claude mcp exec hookdeck get_metrics_queue_depth` in a cron job every minute and pipe the output to a script. If the queue depth is greater than zero, send an alert. You can build simple, rock-solid monitoring without a complex dashboarding tool. Combine `get_metrics_events` with `jq` to parse success rates, or use `list_issues` to check for new failure types. It's all just text, so it works with any standard Unix tool.

Automated Recovery in Your CI/CD Pipelines

This MCP Server gives your deployment scripts eyes and hands. After a deployment, your script can use `publish_event` to run a quick smoke test. It then immediately checks the outcome with `get_event` and `get_attempt`. If an attempt fails, the script can trigger `retry_event` or, for bigger problems, `pause_connection` to halt traffic to the broken deployment. It can even trigger a rollback in your CI system. This turns your pipeline from a simple deployment tool into a resilient delivery system.

Setup guide

Set up Hookdeck (Webhook Gateway) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see hookdeck-webhook-gateway-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Hookdeck (Webhook Gateway) transactions." It will automatically discover and invoke the available Hookdeck (Webhook Gateway) tools.

Terminal

claude mcp add --transport http hookdeck-webhook-gateway-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Hookdeck (Webhook Gateway) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "hookdeck-webhook-gateway-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 (Webhook Gateway) 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 (Webhook Gateway) MCP in Claude Code

It's a single command. Run `claude mcp add --transport http hookdeck -- `. Then verify it's connected with `claude mcp list`. The configuration is saved to your `~/.claude.json` file.

Yes, it's a perfect fit. In your workflow YAML, install the Claude Code CLI, add the server with your token stored as a secret, and then you can run any `claude mcp exec hookdeck ...` command as a step in your job.

For a simple check, just run `claude mcp exec hookdeck count_connections`. You can add this to a monitoring script and compare the output over time to detect unexpected changes in your infrastructure.

First, find the problem using `claude mcp exec hookdeck list_issues`. Then, use the query from the issue to run `claude mcp exec hookdeck bulk_retry_events --query '...'`. It's a two-command fix for potentially thousands of failed events.

Security is handled in the V8 Isolate sandbox where the tool code runs. When using this server, it primarily processes your connection configurations and rules. Any sensitive data inside webhook payloads, accessed via `get_event_raw`, is only held in memory for the duration of that single, ephemeral request.

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