Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Webhook Toolkit

NPM · WEBHOOK-TOOLKIT · 2 COMPONENTS · SCANNED SEP 20

Webhook URLs for AI agents: receive, wait for, replay, sign and verify webhooks (Stripe, GitHub…).

69 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability70
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1989 tokens (~180/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

How do I install the Webhook Toolkit MCP server?

Webhook Toolkit runs locally as an npm package, launched with npx -y webhook-toolkit. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · webhook-toolkit

# add to Claude Code
claude mcp add the-kipdev-webhook-toolkit -- npx -y webhook-toolkit
// .cursor/mcp.json
{
  "mcpServers": {
    "the-kipdev-webhook-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "webhook-toolkit"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "the-kipdev-webhook-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "webhook-toolkit"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add the-kipdev-webhook-toolkit -- npx -y webhook-toolkit
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "the-kipdev-webhook-toolkit": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "webhook-toolkit"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add the-kipdev-webhook-toolkit --command npx --arg -y --arg webhook-toolkit
# ~/.hermes/config.yaml
mcp_servers:
  the-kipdev-webhook-toolkit:
    command: "npx"
    args: ["-y", "webhook-toolkit"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "the-kipdev-webhook-toolkit": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "webhook-toolkit"
      ]
    }
  }
}
# add to Vellum
assistant mcp add the-kipdev-webhook-toolkit -t stdio -c npx -a -y webhook-toolkit
// mcp.json
{
  "mcpServers": {
    "the-kipdev-webhook-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "webhook-toolkit"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +15
    • Malware scan: unverified → pass security
  • 18 Sept 26 54

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/webhook-toolkit@0.1.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 96 packages
Packages resolved 96
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 11 exposed · ~1,859 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
create_webhook_url ~143

Create a public HTTPS URL that captures every HTTP request sent to it (any method, any sub-path). Use it when you need an endpoint to receive a webhook from a third-party service (Stripe, GitHub, Shopify, Slack, Twilio, Clerk…) or from the app you are testing, without deploying or tunnelling anything. Returns the URL, the token the other tools take, and a web inspector link. Anonymous URLs expire after 7 days. Next: configure the sender with the URL, trigger the event, then call wait_for_webhook.

NameTypeReqDescription
namestringLabel shown in the dashboard, e.g. 'stripe-checkout-test'.

No output schema declared.

No examples provided.

explain_webhook_request ~137

AI analysis of a captured webhook: what the event means, its key fields, how its signature is verified and common pitfalls; or, with mode 'handler', a ready-to-use handler in node, python, php, go or ruby. Use it on an unfamiliar payload. Needs WEBHOOK_TOOLKIT_KEY; paid feature with 3 free trials.

NameTypeReqDescription
languagestringHandler language (mode 'handler').
modestring'explain' (default) or 'handler' to generate code.
request_idstringyesCaptured request id.
tokenstringyesWebhook URL token.

No output schema declared.

No examples provided.

get_webhook_request ~88

Get one captured request in full: method, path, query, all headers, raw body (as received, byte-exact for signature checks), detected provider and event. Use it to inspect a payload before writing or fixing a handler.

NameTypeReqDescription
request_idstringyesRequest id from wait_for_webhook or list_webhook_requests.
tokenstringyesWebhook URL token.

No output schema declared.

No examples provided.

list_webhook_requests ~97

List the requests captured by a webhook URL, newest first, with method, path, detected provider/event, size and a short body preview. Use it to see what a service actually sent, then get_webhook_request for one in full.

NameTypeReqDescription
afterstringISO timestamp: only requests newer than this.
limitintegerHow many, default 20.
tokenstringyesWebhook URL token.

No output schema declared.

No examples provided.

list_webhook_urls ~45

List the webhook URLs owned by the account behind WEBHOOK_TOOLKIT_KEY (required). Use it to find the token of an existing permanent URL instead of creating a new one.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

replay_webhook_request ~181

Re-send a captured webhook FROM THIS MACHINE to a URL, localhost included (e.g. http://localhost:3000/api/webhooks), with the same method, headers and body. Use it to iterate on a webhook handler without re-triggering the real event. Returns the handler's status, latency and response. The captured sub-path and query are appended to target_url. Timestamped signatures (Stripe, Slack, Svix, Paddle) are replayed as captured, so strict handlers reject them after ~5 minutes: then use send_signed_webhook.

NameTypeReqDescription
request_idstringyesCaptured request id.
target_urlstringyesWhere to send it, e.g. http://localhost:3000/api/webhooks/stripe (a bare port such as 3000 works).
tokenstringyesWebhook URL token.

No output schema declared.

No examples provided.

send_signed_webhook ~288

Build a webhook with a valid provider signature (Stripe, GitHub, Shopify, Slack, Twilio, Mailgun, Svix/Clerk/Resend, Paddle, Discord with a test key) and POST it FROM THIS MACHINE to your handler (localhost works). Use it to test signature verification and event handling without the real provider. Returns the handler's status and response. Signing happens locally: the secret never leaves the machine.

NameTypeReqDescription
eventstringEvent type, e.g. 'checkout.session.completed', 'push', 'orders/create'.
payloadstringRaw body to sign, sent verbatim (JSON text; Twilio: urlencoded or a JSON object of params). Omit to use a realistic sample of `event`.
providerstringyesSignature scheme. 'svix' also covers Clerk, Resend and Standard Webhooks.
secretstringyesSigning secret, as your handler knows it (Stripe whsec_…, GitHub webhook secret, Twilio auth token, Discord: an Ed25519 test private key in hex).
target_urlstringyesHandler URL, e.g. http://localhost:3000/api/webhooks/stripe (a bare port such as 3000 works).
twilio_urlstringTwilio only: the public URL Twilio would call (default: target_url).

No output schema declared.

No examples provided.

set_webhook_response ~150

Change what a webhook URL answers to senders: status code, body and content type (and optionally its name). Use it to simulate a failing endpoint (e.g. 500 so the provider retries) or to answer a verification challenge that expects a specific body. URLs created with an API key can only be changed with that key.

NameTypeReqDescription
bodystringResponse body.
content_typestringResponse Content-Type, e.g. 'application/json'.
namestringNew label for the URL.
statusintegerHTTP status to answer, e.g. 200, 410, 500.
tokenstringyesWebhook URL token.

No output schema declared.

No examples provided.

sign_webhook_payload ~230

Compute valid signature headers for a webhook body without sending it. Use it to write a test fixture, a curl command, or to check what a provider's signature should be for a given secret. Returns headers, body and a curl command. Runs locally.

NameTypeReqDescription
eventstringEvent type, e.g. 'checkout.session.completed', 'push', 'orders/create'.
payloadstringRaw body to sign, sent verbatim (JSON text; Twilio: urlencoded or a JSON object of params). Omit to use a realistic sample of `event`.
providerstringyesSignature scheme. 'svix' also covers Clerk, Resend and Standard Webhooks.
secretstringyesSigning secret, as your handler knows it (Stripe whsec_…, GitHub webhook secret, Twilio auth token, Discord: an Ed25519 test private key in hex).
timestampintegerUnix seconds to sign with (default: now).
urlstringTwilio only (required for Twilio): the public URL Twilio calls.

No output schema declared.

No examples provided.

verify_webhook_signature ~232

Check whether a webhook signature is valid and, when it is not, explain why: wrong secret, body modified before verification (JSON re-serialised by a parser, trailing newline, CRLF), whitespace in the secret, expired timestamp, or for Twilio the URL form (http vs https, port, query, trailing slash). Use it when a handler rejects deliveries with 'invalid signature'. Runs locally: the secret never leaves the machine.

NameTypeReqDescription
headersobjectyesRequest headers, any casing, e.g. {"stripe-signature": "t=…,v1=…"}.
providerstringyesSignature scheme. 'svix' also covers Clerk, Resend and Standard Webhooks.
raw_bodystringyesThe body exactly as received (e.g. the body field of get_webhook_request).
secretstringyesSigning secret (Discord: the application public key).
tolerance_secondsintegerTimestamp tolerance, default 300. 0 disables the check.
urlstringTwilio only: the full public URL Twilio called.

No output schema declared.

No examples provided.

wait_for_webhook ~268

Block until a webhook reaches a capture URL, then return it (method, path, headers, raw body, detected provider and event type). Use it right after triggering the action that sends the webhook. It is safe to call after the webhook was already sent: requests received since the URL was created in this session, or since the last request this tool returned for the token, are included. Filters skip unrelated deliveries. Calling it again returns the next request. A timeout means nothing matching arrived: check the sender's configuration, then call again.

NameTypeReqDescription
afterstringISO timestamp: only requests strictly newer than this. Overrides the automatic cursor.
body_containsstringOnly requests whose body contains this text.
eventstringOnly this event type, e.g. 'checkout.session.completed', 'push'.
methodstringOnly this HTTP method, e.g. 'POST'.
path_containsstringOnly requests whose sub-path contains this text.
providerstringOnly a request from this sender, e.g. 'stripe', 'github'.
timeout_secondsintegerHow long to wait. Default 60.
tokenstringyesToken returned by create_webhook_url (the last segment of the URL).

No output schema declared.

No examples provided.

Common questions

What is the Webhook Toolkit MCP server?

Webhook Toolkit is an MCP server listed in the public MCP registry as io.github.THE-KIPDEV/webhook-toolkit. Webhook URLs for AI agents: receive, wait for, replay, sign and verify webhooks (Stripe, GitHub…). This page covers its npm package (webhook-toolkit).

Is the Webhook Toolkit MCP server safe to use?

Webhook Toolkit scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Webhook Toolkit MCP server expose?

Webhook Toolkit exposes 11 tools: create_webhook_url, list_webhook_urls, wait_for_webhook, list_webhook_requests, get_webhook_request, and 6 more. Their descriptions and schemas cost roughly 1,859 tokens of context every time the server is loaded.

Is the Webhook Toolkit MCP server still maintained?

Webhook Toolkit is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Webhook Toolkit MCP server under?

Webhook Toolkit declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.