Waitlister Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Waitlister Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An MCP (Model Context Protocol) server that connects AI assistants like Claude, Cursor, and Windsurf to the Waitlister API. Manage your waitlist subscribers through natural language.
Once connected, you can ask your AI assistant things like:
| Tool | Description |
|---|---|
add_subscriber | Add a new subscriber to your waitlist |
list_subscribers | List subscribers with pagination and sorting |
get_subscriber | Get details for a specific subscriber by ID or email |
update_subscriber | Update a subscriber's name, phone, points, or metadata |
log_view | Record a waitlist page view for analytics |
No installation needed — just configure your MCP client:
{
"mcpServers": {
"waitlister": {
"command": "npx",
"args": ["-y", "waitlister-mcp"],
"env": {
"WAITLISTER_API_KEY": "your-api-key",
"WAITLISTER_WAITLIST_KEY": "your-waitlist-key"
}
}
}
}npm install -g waitlister-mcpThen configure:
{
"mcpServers": {
"waitlister": {
"command": "waitlister-mcp",
"env": {
"WAITLISTER_API_KEY": "your-api-key",
"WAITLISTER_WAITLIST_KEY": "your-waitlist-key"
}
}
}
}Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"waitlister": {
"command": "npx",
"args": ["-y", "waitlister-mcp"],
"env": {
"WAITLISTER_API_KEY": "your-api-key",
"WAITLISTER_WAITLIST_KEY": "your-waitlist-key"
}
}
}
}Go to Settings → MCP → Add new MCP server and use the same configuration above.
claude mcp add waitlister -- npx -y waitlister-mcpThen set the environment variables WAITLISTER_API_KEY and WAITLISTER_WAITLIST_KEY.
| Variable | Required | Description |
|---|---|---|
WAITLISTER_API_KEY | Yes | Your Waitlister API key |
WAITLISTER_WAITLIST_KEY | Yes | Your unique waitlist key |
Add a new subscriber to your waitlist.
Parameters:
email (string, required) — Subscriber's email addressname (string, optional) — Subscriber's namephone (string, optional) — Subscriber's phone numberreferred_by (string, optional) — Referral code of the person who referred themmetadata (object, optional) — Custom fields (e.g. { "company": "Acme" })Retrieve a paginated list of subscribers.
Parameters:
limit (number, default 20) — Results per page (1–100)page (number, default 1) — Page numbersort_by (string, default "date") — Sort field: position, points, date, referral_count, emailsort_dir (string, default "desc") — Sort direction: asc or descGet detailed info for a specific subscriber.
Parameters:
id_or_email (string, required) — Subscriber's ID or email addressUpdate a subscriber's information.
Parameters:
id_or_email (string, required) — Subscriber's ID or email addressname (string, optional) — Updated namephone (string, optional) — Updated phone numberpoints (number, optional) — Updated points valuemetadata (object, optional) — Custom fields to add/update (merged with existing)Record a waitlist page view.
Parameters:
visitor_id (string, optional) — Unique visitor identifier (prevents duplicate counts)referring_domain (string, optional) — Referring domainRate limits depend on your Waitlister plan:
| Plan | Subscriber Endpoints | Log View Endpoint |
|---|---|---|
| Growth | 60 requests/min | 200 requests/min |
| Business | 120 requests/min | 400 requests/min |
git clone https://github.com/waitlister/waitlister-mcp.git
cd waitlister-mcp
npm install
npm run buildTest with the MCP Inspector:
WAITLISTER_API_KEY=your-key WAITLISTER_WAITLIST_KEY=your-key npm run inspectMIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.