Lets AI agents inspect, mock, replay, and manage webhook events and integrations.
Also known as gba3124/anyhook-mcp, anyhook-mcp
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.6.2
- Last commit
- Nov 9, 2026
- License
- Apache-2.0
What is AnyHook MCP?
AnyHook lets AI agents inspect, mock, replay, and manage webhook events and integrations.
Summary generated from the project's README
About AnyHook MCP server
AnyHook provides AI agents with the ability to monitor, debug, and manage webhook integrations. It acts as a bridge that gives agents visibility into event logs, allowing them to inspect payloads, verify signatures, and replay failed deliveries. This tool is designed for developers using AI clients like Claude Desktop, Cursor, or Claude Code to manage the entire lifecycle of a webhook, from initial setup to production troubleshooting.
Users can operate the server in two distinct modes. Remote mode requires an ANYHOOK_API_KEY to interact with a live AnyHook account, enabling full access to tools like anyhook_apps_create and anyhook_replay. Local mode requires no account or API key and provides a simulated environment using an in-memory store. This mode is ideal for testing with tools like anyhook_mock to generate signed payloads for providers such as Stripe, GitHub, or Slack. The server can be run via npx or connected as a remote endpoint for browser-based AI interfaces.
What you can do with it
- 1Debug failed webhook deliveriesAn agent can identify events that failed to reach a destination and trigger a replay to fix the issue.
- 2Automate integration setupA developer can instruct an agent to create a new application and provide the necessary inbound URL for a service.
- 3Test local webhook handlersThe agent can generate a signed payload from a specific provider and send it to a local development server.
- 4Verify webhook security signaturesAn agent can manually check if an incoming payload matches a specific secret to troubleshoot authentication errors.
Written from the project's README. Every use case is checked against a quote from it.
How to install AnyHook MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall AnyHook MCP in Claude Code
$ claude mcp add --env 'ANYHOOK_API_KEY=<YOUR_ANYHOOK_API_KEY>' anyhook -- npx -y anyhook-mcpInstall AnyHook MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"anyhook": {
"command": "npx",
"args": [
"-y",
"anyhook-mcp"
],
"env": {
"ANYHOOK_API_KEY": "<YOUR_ANYHOOK_API_KEY>"
}
}
}
}Install AnyHook MCP in VS Code
.vscode/mcp.json
{
"servers": {
"anyhook": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"anyhook-mcp"
],
"env": {
"ANYHOOK_API_KEY": "<YOUR_ANYHOOK_API_KEY>"
}
}
}
}Install AnyHook MCP in VS Code CLI
$ code --add-mcp '{"name":"anyhook","type":"stdio","command":"npx","args":["-y","anyhook-mcp"],"env":{"ANYHOOK_API_KEY":"<YOUR_ANYHOOK_API_KEY>"}}'Install AnyHook MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"anyhook": {
"command": "npx",
"args": [
"-y",
"anyhook-mcp"
],
"env": {
"ANYHOOK_API_KEY": "<YOUR_ANYHOOK_API_KEY>"
}
}
}
}Install AnyHook MCP in Codex
$ codex mcp add anyhook --env 'ANYHOOK_API_KEY=<YOUR_ANYHOOK_API_KEY>' -- npx -y anyhook-mcpInstall AnyHook MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.anyhook] command = "npx" args = ["-y", "anyhook-mcp"] [mcp_servers.anyhook.env] ANYHOOK_API_KEY = "<YOUR_ANYHOOK_API_KEY>"
Install AnyHook MCP in Gemini CLI
$ gemini mcp add -s user -e 'ANYHOOK_API_KEY=<YOUR_ANYHOOK_API_KEY>' anyhook npx -- -y anyhook-mcpInstall AnyHook MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"anyhook": {
"command": "npx",
"args": [
"-y",
"anyhook-mcp"
],
"env": {
"ANYHOOK_API_KEY": "<YOUR_ANYHOOK_API_KEY>"
}
}
}
}Configuration
ANYHOOK_API_KEYSecretPersonal API key from anyhook.net/dashboard/settings/api-keys. Starts with ahk_live_. Optional: without it, the anyhook_quickstart tool can self-provision an account, or tools run against an in-memory store for local dev.
ANYHOOK_API_BASEOverride the API base URL. Defaults to https://anyhook.net. Used by self-hosted AnyHook installations.
| Name | Description | |
|---|---|---|
| ANYHOOK_API_KEY | Personal API key from anyhook.net/dashboard/settings/api-keys. Starts with ahk_live_. Optional: without it, the anyhook_quickstart tool can self-provision an account, or tools run against an in-memory store for local dev. | Secret |
| ANYHOOK_API_BASE | Override the API base URL. Defaults to https://anyhook.net. Used by self-hosted AnyHook installations. |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablegba3124/anyhook-mcp is public and reachablegithub.com/gba3124/anyhook-mcp ↗Pass
- Package names this repository as its sourceanyhook-mcp names gba3124/anyhook-mcp as sourcenpmjs.com/package/anyhook-mcp ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for anyhook-mcpnpmjs.com/package/anyhook-mcp/v/0.6.2#provenance ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-09github.com/gba3124/anyhook-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from anyhook-mcpPass
- No critical advisory in the package or its dependencies99 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 243 msPass
README
View on GitHubanyhook-mcp
An MCP server that gives AI agents eyes on webhooks, inspect events, replay deliveries, mock signed payloads, create apps. Designed for the 45-second AI handler workflow.
Apache 2.0 · npm i -g anyhook-mcp
Forward webhooks to localhost
A public webhook URL that forwards to your machine, with no account:
npx -y anyhook-mcp listen 3000
Webhook URL https://in.anyhook.net/q-3fa9c1d2/listen
Forwards to http://localhost:3000/
This URL is temporary and lasts until Nov 11. To keep it: https://anyhook.net/claim/...
Paste the URL into Stripe, GitHub or any webhook sender. Ctrl-C to stop.
While this is stopped, events are logged but not forwarded.
Connected. Waiting for events.
12:00:03 200 41 ms invoice.paid
12:00:19 500 12 ms invoice.paid AnyHook retries on its schedule
- The URL stays. Restart the command and it is the same URL, so there is nothing to paste into the provider again.
- Signatures verify. Your server gets the bytes the provider sent, so
stripe.webhooks.constructEventand friends work as they do in production. A retry or replay keeps the provider's original timestamp, so a check that refuses old timestamps, like Stripe's default, needs a longer tolerance locally. - Nothing is lost when your laptop is shut. Events are stored either way. A failed delivery is retried, and one that arrived while this was stopped can be replayed.
listen 3000/api/webhooks sets the path. With ANYHOOK_API_KEY set it uses that account, and --app <slug> picks the app. Needs Node 22 or newer.
It is for webhooks, not a general tunnel. The sender gets its answer from AnyHook, so your server's response goes to the event log rather than back to the sender. To expose a whole site, use ngrok or Cloudflare Tunnel.
Already have an AnyHook account?
Connect the hosted endpoint instead of running anything: add https://anyhook.net/mcp
to Claude Code, claude.ai, Codex or VS Code and sign in through the browser, no key
to copy. Steps for each app: https://anyhook.net/mcp.
No account yet (local mode)
No API key needed to start:
claude mcp add anyhook -- npx -y anyhook-mcp
Then ask your agent to run anyhook_quickstart, it creates a free relay
endpoint + API key instantly (no signup), and this MCP session auto-connects.
All account tools (events, replay, apps) work immediately. The response includes
a claim_url to keep the endpoint permanently; unclaimed, it expires in 7 days.
It is a new endpoint, not an account you already have.
What it does
Drop this MCP server into Claude Desktop / Cursor / Claude Code and your agent can:
anyhook_apps_list, see every app in your AnyHook account with its inbound URLanyhook_apps_create, spin up a new app from a promptanyhook_destination_add, forward an existing app's events to a URLanyhook_connect, give a Stripe key or GitHub token: the webhook is registered at the provider and signature-checked from the first event (the key is not stored)anyhook_events, list recent events, filter by app / statusanyhook_inspect, pull a single event's headers and bodyanyhook_replay, re-send a stored event to its destinations (outside the monthly quota, within a daily replay limit and the compute allowance; an event held for quota counts as new)anyhook_undelivered, list events that have not reached a destination: failed, held, still retrying, or logged whilelistenwas stoppedanyhook_usage, the plan's limits and what the account has used of each, with when they resetanyhook_replay_failed, bulk-replay an app's failed events, oldest first (the last 24 hours and 50 per call by default, up to 100), saying when more are waitinganyhook_mock, generate a signed Stripe / GitHub / Slack payload for local handler testinganyhook_verify, verify any incoming signature against your secretanyhook_providers, list the providersanyhook_mockcan generate, with their event types
The inbound URL an app gives you accepts webhook POSTs and also answers provider
setup handshakes automatically: Meta's GET carrying hub.mode=subscribe gets its
hub.challenge echoed back, even before the app is configured, so the URL can be
registered in the Meta App Dashboard first and wired up after.
Two modes:
| Mode | When | What works |
|---|---|---|
| remote | ANYHOOK_API_KEY is set |
All tools above, live against your AnyHook account |
| local | No API key | Provider toolkit (mock / verify / providers) + an in-memory store you can simulate events into. Useful for trying it out before signing up. |
Quick start
npm install -g anyhook-mcp
# or run without installing
npx -y anyhook-mcp
Get an API key from https://anyhook.net/dashboard/settings. Keys start with ahk_live_.
Install in Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"anyhook": {
"command": "npx",
"args": ["-y", "anyhook-mcp"],
"env": {
"ANYHOOK_API_KEY": "ahk_live_xxxxxxxx"
}
}
}
}
Restart Claude Desktop. The tools appear under the hammer icon.
Install in Cursor
Open Settings → MCP → Add new MCP server. Or edit ~/.cursor/mcp.json:
{
"mcpServers": {
"anyhook": {
"command": "npx",
"args": ["-y", "anyhook-mcp"],
"env": {
"ANYHOOK_API_KEY": "ahk_live_xxxxxxxx"
}
}
}
}
Install in Claude Code
claude mcp add anyhook -e ANYHOOK_API_KEY=ahk_live_xxxxxxxx -- npx -y anyhook-mcp
Or add the same mcpServers entry to your project's .mcp.json.
Remote endpoint (no local process)
The same server is hosted at https://anyhook.net/mcp (streamable HTTP,
stateless). Claude Code, claude.ai, Codex and VS Code sign in through the
browser (OAuth), no key to copy: https://anyhook.net/mcp has the steps for
each. Any other client sends Authorization: Bearer ahk_live_... with a key
from the dashboard:
{ "mcpServers": { "anyhook": { "url": "https://anyhook.net/mcp", "headers": { "Authorization": "Bearer ahk_live_..." } } } }
The endpoint has no anyhook_quickstart: that tool exists only in local mode.
Local-only mode (no account needed)
Skip the env var:
{
"mcpServers": {
"anyhook": {
"command": "npx",
"args": ["-y", "anyhook-mcp"]
}
}
}
The agent gets anyhook_mock, anyhook_verify, anyhook_providers, anyhook_simulate, anyhook_events (against memory store), and anyhook_inspect (against memory store). Useful for "generate me a signed Stripe payment_intent.succeeded and POST it to localhost:3000" flows during local dev.
Example conversations
Triage a failing endpoint:
"Show me undelivered events for the
stripe-prodapp from the last hour, then replay them."
The agent calls anyhook_undelivered then anyhook_replay for each, surfacing the responses inline.
Create an app for a new integration:
"Make a new AnyHook app called
replicate-video-jobs, sourcegeneric, point it athttps://my-app.vercel.app/api/replicate-callback."
Calls anyhook_apps_create, returns the inbound URL you paste into Replicate.
Sanity-check a signature failure:
"Here's an inbound payload from Stripe that AnyHook is rejecting. Verify the signature manually with secret
whsec_xxx."
Calls anyhook_verify with the supplied headers + body + secret and returns valid, with what to check when it is false.
Mock a webhook for local testing:
"Generate a Stripe
payment_intent.succeededevent and POST it to http://localhost:3000/api/webhooks/stripe."
Calls anyhook_mock with targetUrl set; returns the request that was sent + your handler's response.
Environment variables
| Var | Required | Default | Purpose |
|---|---|---|---|
ANYHOOK_API_KEY |
for remote mode | - | ahk_live_* from https://anyhook.net/dashboard/settings |
ANYHOOK_API_BASE |
no | https://anyhook.net |
Override for self-hosted AnyHook deployments |
Why this is interesting
AI agents have been blind to their own webhook infrastructure. They can write the integration code, but once an event misbehaves in production they can't see it, you tell them what happened. With this MCP server, Claude / Cursor can read the actual event log, replay deliveries, debug signature failures, and even spin up new apps. It closes the loop between writing webhook code and operating it.
License
Apache-2.0 © AnyHook
AnyHook MCP questions
How do I add AnyHook MCP to Claude Code?
Run claude mcp add --env 'ANYHOOK_API_KEY=<YOUR_ANYHOOK_API_KEY>' anyhook -- npx -y anyhook-mcp in your terminal. Add --scope user to make it available in every project.
How do I add AnyHook MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I keep my webhook URL from expiring?
Temporary URLs can be made permanent by using the claim URL provided in the response.
Does AnyHook support signature verification?
Yes, it allows you to verify incoming signatures against your secret and ensures your server receives the original bytes for production-like testing.
What happens to events if my local machine is turned off?
Events are not lost; they are stored and can be replayed once your service is back online.