MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
MCP Events bridge is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
7
tools declared
local
runs on your machine
—
downloads a day
What it does
Turn webhooks into MCP Events that AI agents subscribe to, with Hookdeck Event Gateway.
Quickstart
This package runs as a local HTTP server (Streamable HTTP), not over stdio, so a client cannot start it as a process. Start it in a terminal with npx -y @hookdeck/mcp-events-bridge and keep it running, then add the address it listens on to your client as a remote server; that address is not recorded here, so there is no entry to copy.
Publishernot claimed
HOAll 1 server
hookdeck1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts MCP Events bridge as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This package runs as a local HTTP server (Streamable HTTP), not over stdio, so a client cannot start it as a process. Start it in a terminal with npx -y @hookdeck/mcp-events-bridge and keep it running, then add the address it listens on to your client as a remote server; that address is not recorded here, so there is no entry to copy.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Get one past event by its name and eventId, as an MCP Events delivery or list_events gives them, read from Hookdeck Event Gateway.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | The event name, such as resend.email.received |
| eventId | string | yes | The event's id from a delivery or list_events. It's the service's own id (such as a Resend svix-id), so it's unique only together with name. |
List past events, newest first by timestamp, from every source or for one event name, read from Hookdeck Event Gateway.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | An event name, such as resend.email.received. Omit for every source. |
| since | string | no | Only events Event Gateway received at or after this time, in ISO 8601, e.g. 2026-11-04T09:00:00Z. It compares received time, not the event's timestamp. |
| limit | integer | no | At most this many events (default 20, at most 100). |
List the configured sources (the services events come from): each one's id, type, event types and webhook subscription count.
No parameter schema on file.
Get events that happened since your cursor, for clients that can't subscribe with MCP Events (events/subscribe). Same as events/poll.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| maxAgeMs | integer | no | With a cursor, skip events older than this many milliseconds. |
| maxEvents | integer | no | At most this many events (default 50, at most …). |
Wait for the next events after your cursor, returning as soon as there are some, or with none after timeoutMs (default … s, at most … s).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| timeoutMs | integer | no | How long to wait, in milliseconds (default …). |
Create a public callback URL for MCP Events webhook delivery, for an agent on this machine with no public URL of its own, then pass it to events/subscribe.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent | string | yes | Your agent or machine name (up to 40 letters, digits or _), e.g. "laptop". It names an Event Gateway destination shared by its URLs, so keep it unique in the Hookdeck project. |
| name | string | yes | A name for this URL (up to 40 letters, digits or _), e.g. "email_from_alice". Reusing a name with the same secret returns that URL. |
| port | integer | no | Local port your agent receives deliveries on. Set by the agent's first URL (default …) and shared by the rest. |
| path | string | no | Local path deliveries are forwarded to. Set by the agent's first URL (default …) and shared by the rest. |
| secret | string | no | The whsec_ secret you will subscribe with. One URL holds one secret: to rotate, create a URL with a new name. Omit for a pass-through URL. |
List the callback URLs an agent created with create_callback_url, with each one's local port and path and whether it's pass-through. Check here before creating a URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent | string | yes | Your agent or machine name (up to 40 letters, digits or _), e.g. "laptop". It names an Event Gateway destination shared by its URLs, so keep it unique in the Hookdeck project. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install MCP Events bridge or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 0.10.0 · scanned 6 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings2 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest25e664f7de3299d8a80ebdbcf313a01d3b3ed44ed53d785de57cb999acaccfc1
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (7 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
2 of the 7 recovered tools are registered only when poll holds (dist/core/mcp.js:69) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 3.
2 of the 7 recovered tools are registered only when callbacks holds (dist/core/mcp.js:122) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 3.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
3 tools are registered unconditionally · (1) 2 more only when poll holds (dist/core/mcp.js:69) · (2) 2 more only when callbacks holds (dist/core/mcp.js:122) — typically when a key or option is configured. All 7 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_event | untrusted-input | untrusted-input: keyword "browse" |
| list_events | no tags | |
| list_sources | no tags | |
| poll_events conditional (1) | no tags | |
| wait_for_event conditional (1) | no tags | |
| create_callback_url conditional (2) | external-sink | external-sink: keyword "webhook" |
| list_callback_urls conditional (2) | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest25e664f7de3299d8
Scanned2026-11-06
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.10.0. Pin a release below and the command asks for exactly that one.
0.10.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish MCP Events bridge can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.