MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Waitlister 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.
96/100
trust score
4
downloads a day
local
runs on your machine
233
downloads in 30d
What it does
Official MCP server for the Waitlister API — create waitlists and manage subscribers through AI assistants like Claude, Cursor, and more. Account-key support: works on every plan. (Successor to the waitlister-mcp package.)
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user waitlister-mcp '--' npx -y @waitlister/mcp
# 2 — ask your agent for something these tools do
# create_waitlist, get_account, list_waitlists and 12 more
Waitlister costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
WAAll 1 server
@waitlister1 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 Waitlister 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.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user waitlister-mcp '--' npx -y @waitlister/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take WAITLISTER_ACCOUNT_KEY (Account API key (wl_acct_…) from waitlister.me Settings → API keys. Works on every plan; enables waitlist creation and all landing-page tools.), WAITLISTER_API_KEY (Legacy alternative: per-waitlist API key (wl_…, Growth+ plans) used together with WAITLISTER_WAITLIST_KEY.), WAITLISTER_WAITLIST_KEY (Default waitlist key for per-waitlist-key mode or to scope tools to one waitlist.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Create a new waitlist on your Waitlister account (requires an account key, works on every plan within its waitlist cap). Returns the waitlist key and a form_action_url that collects signups immediately. Pass landing_page to also provision the hosted landing page (as a draft — go live with…
No parameter schema on file.
Check the configured API key and what this account may do — the cheapest first call, and the one to make when anything looks misconfigured. Returns the account, the plan name, whether the general API is available, how many waitlists the account has against its cap, whether creating another would…
No parameter schema on file.
List every waitlist your account owns, with subscriber and view counts (requires an account key).
No parameter schema on file.
Get a waitlist's subscriber and view counters — cheap social proof, works on every plan. Counters update asynchronously (within seconds of a signup or delete).
No parameter schema on file.
Add a new subscriber to a waitlist. Returns their position, referral code, and sign-up token. Idempotent per email: an existing email returns is_new_sign_up: false with their current position, not an error. Works on every plan.
No parameter schema on file.
Retrieve a paginated list of a waitlist's subscribers, sortable by position, points, date, referral_count, or email. Requires the Growth plan or higher.
No parameter schema on file.
Retrieve detailed information about a specific subscriber by their ID or email address — position, points, referral info, metadata, location, and more. Requires the Growth plan or higher.
No parameter schema on file.
Update an existing subscriber's name, phone, points, and/or custom metadata. Only include fields you want to change; updating points triggers a queue position recalculation. Requires the Growth plan or higher.
No parameter schema on file.
Permanently delete a subscriber (and their email history) from a waitlist by ID or email address. This cannot be undone. Counters and queue positions update asynchronously within a few seconds. Requires the Growth plan or higher.
No parameter schema on file.
Record a view of a waitlist page — useful for tracking engagement and conversion rates when you host your own landing page.
No parameter schema on file.
Get the structured view of a waitlist's hosted landing page: status (draft/published/unpublished), page_type (standard or ai), copy fields, theme, SEO, the live URL (null until published), and view/signup analytics. AI-built pages also return remaining AI credits. Works on every plan. 404 if the…
No parameter schema on file.
Create the waitlist's hosted landing page from structured fields, as a draft (nothing goes live until publish_landing_page). One page per waitlist — returns a 409 error if one already exists (use update_landing_page then). headline is required. Works on every plan. Tip: when creating a new…
No parameter schema on file.
Update any subset of the landing page's structured fields. On a published page the change goes live immediately. IMPORTANT: on an AI-built page (page_type "ai"), the copy/structure fields (headline, description, button_text, collect_name, collect_phone, background) return a 409 error — edit those…
No parameter schema on file.
Publish the landing page to its live URL (https://waitlister.me/p/{slug}, or the waitlist's custom domain) — or take it offline with unpublish: true. Publishing validates the page has an email field, a submit button, and a headline of at least 3 characters. API publishes skip the custom…
No parameter schema on file.
Generate a complete custom landing page from a natural-language prompt with Waitlister's AI builder (same engine as the dashboard), or edit the existing AI page with is_edit: true. COSTS 1 AI CREDIT per call (shared with the dashboard AI builder; errors with the balance when out of credits) —…
No parameter schema on file.
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 Waitlister 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 96 / 100
Release 1.4.0 · scanned 15 Oct 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 score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest60c01374249813588a7f9959af34949be2ba0176353ba8e5309a9fb013dc8d5a
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 (15 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>".
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.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| create_waitlist | no tags | |
| get_account | no tags | |
| list_waitlists | no tags | |
| get_stats | no tags | |
| add_subscriber | no tags | |
| list_subscribers | no tags | |
| get_subscriber | no tags | |
| update_subscriber | no tags | |
| delete_subscriber | no tags | |
| log_view | no tags | |
| get_landing_page | no tags | |
| create_landing_page | state-write | state-write: declares readOnlyHint: false |
| update_landing_page | state-write | state-write: declares readOnlyHint: false |
| publish_landing_page | state-write | state-write: declares readOnlyHint: false |
| generate_landing_page | state-write | state-write: declares readOnlyHint: false |
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest60c0137424981358
Scanned2026-10-15
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 1.4.0. Pin a release below and the command asks for exactly that one.
1.4.0
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 Waitlister 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.