Webhooks by Wakeshift MCP server
Commit 6. Nov. 2026Ermöglicht es AI Agents, in Echtzeit auf Events von Services wie GitHub, Stripe und Linear über eine dedizierte Webhook-URL zu reagieren.
Auch bekannt als wakeshift/apps, webhooks
- Stars
- 0
- Tools
- —
- Downloads, 30 Tage
- —
- Neueste Version
- 1.0.0
- Letzter Commit
- 6. Nov. 2026
- Lizenz
- Apache-2.0
Was ist Webhooks by Wakeshift MCP?
Ermöglicht es AI Agents, in Echtzeit auf Events von Services wie GitHub, Stripe und Linear über eine dedizierte Webhook-URL zu reagieren.
Zusammenfassung generiert aus dem README des Projekts
Über Webhooks by Wakeshift MCP server
Webhooks by Wakeshift bietet AI Agents eine Möglichkeit, in Echtzeit auf externe Events über eine dedizierte Webhook-URL zu reagieren. Dieser Server fungiert als Brücke zwischen Drittanbieter-Services und MCP Clients wie Claude Code, Cursor oder Copilot CLI. Durch die Nutzung des watch Tools kann ein Agent POST-Requests von Plattformen wie GitHub, Stripe und Linear abonnieren. So kann die KI sofort reagieren, wenn ein Workflow abgeschlossen wird, eine Zahlung fehlschlägt oder ein Issue erstellt wird.
Das System ist stateless und sicher konzipiert und nutzt signierte Links, um Credentials abzuleiten, ohne sensible Session-Daten zu speichern. Nutzer können den Server lokal mit einer Postgres-Datenbank und einem Wakeshift API Key hosten oder die gehostete Version unter try.wakeshift.ai nutzen. Er enthält spezialisierte Tools wie watch, unwatch, recent_posts und webhook_info zur Verwaltung von Subscriptions. Der Server unterstützt zudem die Signature Verification für GitHub und Stripe, um sicherzustellen, dass nur authentische Events den Agent triggern.
Was du damit machen kannst
- 1GitHub Workflow Status überwachenBitte einen AI Agent, auf das Abschließen spezifischer GitHub Workflows zu achten, um Build-Fehler zu tracken.
- 2Stripe Payment Events trackenLass einen Agenten in Echtzeit auf fehlgeschlagene Stripe-Rechnungen oder erfolgreiche Zahlungen reagieren.
- 3Linear Issue Updates verwaltenAnweise einen Agenten, Linear auf neue Issue-Erstellungen zu überwachen, um das Task-Management zu automatisieren.
- 4Kürzliche Webhook-Aktivitäten prüfenNutze den Agenten, um eine Historie der letzten eingehenden Posts abzurufen und die Event-Zustellung zu verifizieren.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du Webhooks by Wakeshift MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenWebhooks by Wakeshift MCP in Claude Code installieren
$ claude mcp add --transport http webhooks https://try.wakeshift.ai/t/%7Blink%7D/mcpWebhooks by Wakeshift MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"webhooks": {
"url": "https://try.wakeshift.ai/t/%7Blink%7D/mcp"
}
}
}Webhooks by Wakeshift MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"webhooks": {
"type": "http",
"url": "https://try.wakeshift.ai/t/%7Blink%7D/mcp"
}
}
}Webhooks by Wakeshift MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"webhooks","type":"http","url":"https://try.wakeshift.ai/t/%7Blink%7D/mcp"}'Webhooks by Wakeshift MCP in Codex installieren
$ codex mcp add webhooks --url https://try.wakeshift.ai/t/%7Blink%7D/mcpWebhooks by Wakeshift MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.webhooks] url = "https://try.wakeshift.ai/t/%7Blink%7D/mcp"
Webhooks by Wakeshift MCP in Gemini CLI installieren
$ gemini mcp add -s user --transport http webhooks https://try.wakeshift.ai/t/%7Blink%7D/mcpWebhooks by Wakeshift MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"webhooks": {
"url": "https://try.wakeshift.ai/t/%7Blink%7D/mcp",
"type": "http"
}
}
}Automatisierte Checks
Geluften am 14. Nov. 2026Vollständiger Bericht →Noch nicht verifiziert. Ein Server benötigt einen Score von 80, keine kritischen Befunde und genug Daten für unsere Prüfung. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbarwakeshift/apps is public and reachablegithub.com/wakeshift/apps ↗Bestanden
- Paket nennt dieses Repository als QuelleNicht geprüft
- Build-Provenienz (Sigstore-Attestierung)Nicht geprüft
- Open Source Lizenz (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-11-06github.com/wakeshift/apps ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNicht geprüft
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
- Keine versteckten Anweisungen an das Modell0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNicht geprüft
- Remote-Endpoint beantwortet den MCP-HandshakeEndpoint did not answer initialize: HTTP 404Befund
README
Auf GitHub ansehenWebhooks
A webhook URL that wakes your agent: get a link, add it to your agent (Claude Code, Codex, Cursor, Antigravity, opencode, Copilot CLI or any MCP client), ask the agent to watch, and every POST to your webhook URL (curl, Postman, GitHub, Stripe, Linear, your own app) wakes it. Wakeshift runs it at try.wakeshift.ai. Built on the TypeScript SDK, @wakeshift/sdk.
How it works
- Stateless links. A link's code is signed with
TRY_SECRETand names a random webhook ID and when it was made. The MCP URL (/t/<code>/mcp), the page (/l/<code>), the webhook URLs (/in/<token>, one token per signature check) and the signing secret are all derived from it. Nothing is stored. A link expires after 7 days without use; when it was last used is kept in the database (written at most every 5 minutes per instance). When it expires, Wakeshift is asked to forget the webhook (forgetUserwith the webhook ID, which is the app's user for it): its workspace, the conversations that watched it, their subscriptions and deliveries. The sweep queues it in the database in the transaction that deletes the link's own rows, and every instance works the queue every 10 minutes, retrying a failure with backoff (a minute, doubling, at most 6 hours) until Wakeshift says it's done. - The SDK user is the webhook; posts are an event.
webhook.received(argument: the webhook's ID; only the webhook's own SDK user, anyone with its link, may subscribe) carries what was posted:summary, a line saying what happened, then the parsed body and the headers that say who sent it. Every tool is wrapped withattached.events(the handlewake.attachreturns), and takes Wakeshift's arguments throughattached.inputs.watchsubscribes the calling conversation withcall.subscribe;unwatchends it withcall.unsubscribe. The wrapper adds one Wakeshift block to each tool's result: how the conversation is woken after a subscribe, pending messages and a Codex thread's beacon otherwise. A call that fails ends the subscription it made. A client that speaks MCP Events (ChatGPT) gets no conversation subscription: the block tells it to subscribe towebhook.receiveditself. A post becomesevent.emit.wake.attachaddssubscribe_events,unsubscribe_eventsandlist_subscriptions. - MCP: Streamable HTTP with sessions, no sign-in (the code in the URL is the credential). Nothing about a session lives in an instance: initialize's client name, version and capabilities are stored under the
Mcp-Session-Id, and each request builds the MCP server afresh from them on whichever instance it reaches (the SDK's transport in stateless mode; the session ID is checked here, 404 if unknown or another link's). So sessions survive restarts and need no affinity, and the client's name and capabilities (which decide how Cursor, opencode and the rest are woken, and whether a client subscribes itself) are right on every instance: the rebuilt server answersgetClientVersionandgetClientCapabilitiesfrom the stored initialize, and the wrapper reads them. Sessions idle for 7 days are dropped (the client initializes again). Tools:watch,unwatch,recent_posts,webhook_info. - Webhooks:
POST,PUTorPATCH/in/<token>, any body up to 64 KB. The event'stextsays what happened: for GitHub (fromX-GitHub-Event)GitHub workflow_run completed: failure on main (tests) in acme/api; for StripeStripe invoice.payment_failed: in_…, USD 49.00, open (evt_…, test mode); for LinearLinear Issue create: ENG-123 Checkout page 500s; for anything elsePOST to your webhook(with(empty body)if it was), since the data has the rest: the text doesn't repeat the body, so a small post's data fits on one Monitor line (480 bytes) in full. Itsdatais the parsed body (body, orbody_base64), the method, content type, a few headers that say who sent it (includingLinear-EventandLinear-Delivery; never Authorization, cookies or signatures) and, for Stripe and Linear,source(the event type and ID). Retries are one publish: byIdempotency-Key,X-GitHub-Delivery,Linear-Delivery, or a Stripe event'sevt_ID. On a GitHub, Stripe or Linear URL only the service's own ID counts (Idempotency-Keyisn't signed, so a captured delivery replayed with a fresh one would wake the agent again); a Stripe URL uses only theevt_ID from the signed body.GETexplains how to post; a body more than 256 KB over the limit has its connection dropped rather than read. - Signature checks: the page's tabs give a URL per check, each its own token, so a checked URL can't be turned into the open one; the open URL keeps working for whoever has it, until the user replaces it (below). GitHub's
X-Hub-Signature-256andAuthorization: Beareruse secrets derived per webhook and per check (try_gh_…,try_bearer_…). Stripe and Linear make their own secret: the user pastes it into the page, and it's sealed into that URL's token (AES-256-GCM with a key derived fromTRY_SECRET). It's stored only in that form: the URL is kept as the webhook's checked URL (below) until the link expires. Stripe'sStripe-Signature(t=…,v1=…, HMAC-SHA256 oft.body) must be within 5 minutes; Linear'sLinear-Signature(hex HMAC-SHA256 of the body) needs awebhookTimestampwithin a minute. - A new open URL: the open tab's "Get a new URL" (
POST /l/<code>/rotate) replaces the open URL. Its token then carries the webhook's open-URL generation, kept per webhook in the database (hooks.open_gen), and a post or GET to an open URL of any other generation gets 410 (replaced), on every instance at once. The webhook ID (the SDK user, so its subscriptions), the link and MCP URL, the history and the checked URLs stay as they were, and the live view gets a line saying the URL changed. Only the link's code can ask (a webhook URL is a different capability, and can't), from this site's page: a request whoseOriginorSec-Fetch-Sitesays another site sent it gets 403. Ten an hour per webhook (429 past that). - Which URL the agent hears about:
watchandwebhook_infogive the checked URL the user last picked (a GitHub or bearer tab they opened, a Stripe or Linear URL they made, or the URL a service last posted to), and say which check it uses. It's kept for as long as the link lives. - Limits (counted in the database, atomically, so they hold across instances; fixed windows: the hour and the UTC day): 60 posts an hour and 500 a day for each of a webhook's URLs (429 with
Retry-After), so whoever has the open URL can't use up the checked one's. Refused posts (401, 413) don't count; retries do (each is still a request to Wakeshift, so a repeatedIdempotency-Keycan't get round the limits). 20,000 an hour across all webhooks, 30 new links an hour per address (an IPv6 address by its /64; kept as an HMAC of the address, for the hour).TRY_PER_HOUR,TRY_PER_DAY,TRY_GLOBAL_PER_HOURandTRY_LINKS_PER_HOURchange them, and the terms and privacy policy state the limits in use. - Overload: an instance takes 256 requests in flight (posts three quarters of that, so pages and tool calls keep some room) and 900 open streams (live views, MCP GET and listen streams); for one webhook, at most 20 live views and, apart, 20 agents' streams, so agents can't leave the page without one; 2 GET streams for one MCP session (a live view past that gets 429, a GET stream 405); past that, and when the database is away or out of connections, it answers 503 with
Retry-Afterand a plain message (JSON for webhooks, JSON-RPC for MCP, a page for pages), never a 500. A link's page still comes up when the database is slow, without its history; the live view retries and says so (below). Wakeshift's own 429 or 503 on publish becomes a 503 withRetry-Afterfor the poster. - The page's live view is SSE from this server (
/l/<code>/live): each post (received, refused, rate limited, the start of what was posted, and how many watching conversations the publish reached), and each watch and unwatch. Lines are kept in the database (the last 50 per webhook) and reach pages on every instance byNOTIFYon the webhook's channel (try_<hook>; each instanceLISTENs only for webhooks it has a page open for, and replays the recent lines whenever its connection comes back after a drop; it pings that connection every 30 seconds so a silent drop is noticed). A webhook's refused and rate-limited posts get at most 10 lines a minute per instance, so a flood of bad signatures doesn't push real posts out. The rest are counted, and once the minute is over (or the instance stops) each instance adds its count to the webhook's one line for that minute, which the page updates in place: one line a minute with the total across instances, written at most once a minute per webhook by each instance. A live view that doesn't keep up with what's written to it is dropped (EventSource reconnects). Each line goes with itsseqas its SSE ID, and a live view asks for the lines after the newest it has (?after=<seq>, orLast-Event-IDwhen EventSource reconnects by itself), so after a gap it shows what happened meanwhile (as far as the last 50 go). When the server refuses it (429, 503), EventSource gives up; the page tries again after 2 seconds, doubling to 30 at most (randomized a little), back to 2 once connected, and at once when the page is looked at again, the network comes back or the status poll gets an answer (liveConnectionin page.ts). The page shows who calledwatch, "sent to N watching conversations" per post, and whether an agent is connected right now and how (stream, hooks or polling): it polls/l/<code>/statusevery 10 seconds, which asks Wakeshift forwebhook.received's status with the webhook's ID (event.status, read-only).
Run it yourself
-
In the Wakeshift console, open Build → New app and copy its key (
wst_…). -
Create an empty Postgres database. Webhooks creates its tables when it starts (
migrations/). -
Build the SDK, then Webhooks, from the repository's root:
(cd third_party/wakeshift-node && npm ci && npm run build) cd webhooks && npm ci && npm run build -
Copy
.env.exampleto.env, fill it in, and run it:Variable WAKESHIFT_KEYThe app's key from step 1 WAKESHIFT_COREWakeshift's URL (default https://app.wakeshift.ai)TRY_SECRETSigns links; 32 or more random bytes. Changing it ends every link TRY_DATABASE_URLThe database from step 2; every instance shares it TRY_DB_POOLConnections per instance (default 3), plus one that listens for the live view PUBLIC_URLYour copy's public URL (default http://localhost:$PORT)PORTListen port (default 8380) TRY_PROXY_HOPSProxies in front of it that append to X-Forwarded-For(Google's load balancer: 2); 0 uses the socket's addressTRY_PER_HOUR,TRY_PER_DAY,TRY_GLOBAL_PER_HOUR,TRY_LINKS_PER_HOUROptional: the limits above set -a; . ./.env; set +a npm start -
Open
PUBLIC_URL, get a link, and run the command its tab for your agent shows.
Testing
npm run lint
npm test # unit tests; needs WAKESHIFT_TEST_DATABASE_URL, a Postgres URL for a role that can create databases
The end-to-end and load tests run Webhooks against the Wakeshift server, so they run in Wakeshift's own repository.
Contributing
This repository is generated from Wakeshift's main repository. Pull requests are welcome: we apply them there and publish the result. See CONTRIBUTING.
Webhooks by Wakeshift MCP Fragen
Wie füge ich Webhooks by Wakeshift MCP zu Claude Code hinzu?
Führe claude mcp add --transport http webhooks https://try.wakeshift.ai/t/%7Blink%7D/mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich Webhooks by Wakeshift MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Wie nutze ich das mit meinem AI Agent?
Hol dir einen Link vom Service, füge ihn deinem Agenten hinzu (wie Claude Code, Cursor oder Copilot CLI) und bitte den Agenten, den Webhook zu überwachen.
Welche Services können meinen Agent triggern?
Der Server unterstützt GitHub, Stripe und Linear, kann aber auch POST-Requests von jeder beliebigen benutzerdefinierten Anwendung empfangen.
Wie lange sind die Webhook-Links gültig?
Die Links sind stateless und laufen nach 7 Tagen Inaktivität ab.