The webhook tunnel your AI agent can use

Pipehero exposes your localhost on a public URL and captures every webhook — and it ships a remote MCP server, so the agent in your editor can read the exact payload a provider sent, correlate it with your code, fix the handler and replay the webhook to confirm. No copy-pasting JSON into a chat.

claude mcp add --transport http pipehero https://mcp.pipehero.app/mcp

One click from there: your browser opens, you approve, and the tools are live (OAuth — no token to paste).

Why an agent + your webhooks

Debugging a webhook handler means juggling three things: what the provider actually sent, what your code expects, and a way to re-trigger the event. Your agent already has your codebase. Pipehero's MCP tools give it the other two — the captured request (headers, raw body, signature status, response) and one-call replay to localhost. That closes the loop: the agent can diagnose a 500 from the real payload, patch the handler, and verify the fix against your running app.

Connect your client

Claude Code

One command. Your browser opens to sign in and approve — no token to paste.

claude mcp add --transport http pipehero https://mcp.pipehero.app/mcp

Cursor

Add the server to ~/.cursor/mcp.json (or the project's .cursor/mcp.json):

{ "mcpServers": { "pipehero": { "url": "https://mcp.pipehero.app/mcp" } } }

Claude Desktop

Settings → Connectors → Add custom connector, then paste the URL:

https://mcp.pipehero.app/mcp

VS Code (Copilot)

One command from your terminal:

code --add-mcp '{"name":"pipehero","type":"http","url":"https://mcp.pipehero.app/mcp"}'

Headless / CI? Pass a token from Settings as an Authorization: Bearer header. Prefer local? The CLI doubles as a stdio server: pipehero mcp. Details in the docs.

The tools

list_tunnelsYour tunnels and whether each is online.
list_requests(subdomain)Recent captured webhooks for a tunnel.
get_request(subdomain, id)Full request + response (headers + body).
replay_request(subdomain, id)Replay a webhook to your localhost.
send_test_webhook(subdomain, …)Fire a test webhook at your tunnel. (Pro)

Published on the official MCP registry as io.github.pipehero/pipehero, with read-only/destructive annotations on every tool.

Prompts that just work

  • The last webhook to myapp returned 500 — read the payload and my handler and tell me why it failed.
  • Fix the handler, then replay the webhook to confirm it works.
  • Compare what Stripe sent to what my code expects and flag any mismatch.
  • Show me every failed (non-2xx) webhook and what they had in common.

Want the agent to reach for Pipehero on its own? pipehero skill install drops a skill into ~/.claude/skills that teaches it when and how.

FAQ

What is an MCP webhook tunnel?

A localhost tunnel that also exposes its captured webhooks to AI agents over the Model Context Protocol (MCP). Your agent can list tunnels, read the exact payload and headers a provider sent, and replay a webhook to your local handler — instead of you copy-pasting JSON into the chat.

Which AI agents and editors work with Pipehero's MCP server?

Any MCP client: Claude Code, Claude Desktop, Cursor, Windsurf, VS Code with Copilot, Zed and others. The server is remote (Streamable HTTP), so most clients connect with just the URL — https://mcp.pipehero.app/mcp.

Do I need to paste an API token?

No. The server supports OAuth: your client opens the browser, you sign in and approve, done. For CI or headless use you can pass a token from Settings as an Authorization: Bearer header instead.

Can the agent break anything?

The tools are scoped to your workspace and annotated: reading tunnels and requests is read-only; replay is explicitly marked as a write action, so well-behaved clients ask before running it.

Is MCP available on the free plan?

Yes — MCP access is included on every plan, including Free.

The other direction: built your own MCP server and need a cloud client (Claude.ai, ChatGPT) to reach it? See the MCP server tunnel.

Provider guides

Start debugging webhooks in a minute

Free plan, no credit card. Expose localhost, inspect and replay every webhook.

Get started free