New-hire onboarding plans: one hire at a time or a whole cohort from a role template. You add a hire (name, role, start day), build their task plan with owners (hr, manager or it) and due dates counted from the start, or apply a role template once and let every hire in that role inherit it with the template's version recorded. Mark tasks done or skipped as they happen (skipped is a deliberate dismissal that never counts as done), watch percent complete and overdue per hire, and onboarding_overdue lists everything still outstanding past its due date, most overdue first. Editing a template after applying it never changes a hire who already copied it.
onboarding_hire_list, onboarding_progress and onboarding_overdue are free, unlimited and write nothing, so leave them enabled permanently and check the board as often as you like. onboarding_task_done is the deliberate one: done and skipped are separate marks, and a skipped task never counts as complete.
| You say | Tool |
|---|---|
| Ada Lovelace starts Monday as analytics-engineer; set her up. | onboarding_hire_add |
| Apply the analytics-engineer template to her plan. | onboarding_template_apply |
| What is still outstanding for Ada, and anything overdue across the team? | onboarding_progress then onboarding_overdue |
The unit suite is 18 tests, 18 passing, 0 failing (node --test, node v22), covering the template copy and version stamp, the done/skipped split and the overdue ordering; adversarial, concurrency and contract suites sit alongside it.
The file is .cursor/mcp.json, and the key inside it is mcpServers.
| Scope | Path |
|---|---|
| This project only | <project>/.cursor/mcp.json |
| Every project | ~/.cursor/mcp.json |
If you also run Claude Desktop, the shortest path there is one click: onboarding.mcpb
from the latest release opens as an extension, with no JSON and no terminal.
Cursor reads its own config, so here it is:
The config block:
{
"mcpServers": {
"onboarding": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/mcp-servers/servers/onboarding/dist/index.js"]
}
}
}
The node command above wants a built file. From a clone, once:
git clone https://github.com/theluckystrike/mcp-servers.git
cd mcp-servers && npm install
npm run build -w packages/mcp-license -w servers/onboarding
That writes servers/onboarding/dist/index.js, and its absolute path is the one argument
the config needs.
The npm packages are not published yet, so the form below returns a 404 today. It is here because it is what the entry becomes the day the publish lands, with nothing else changed:
{
"mcpServers": {
"onboarding": {
"command": "npx",
"args": ["-y", "@theluckystrike/mcp-onboarding"]
}
}
}
The Customize page shows the server and its tools once it has started.
Nothing is published to npm yet, so the working install paths are the ones above: the .mcpb bundle from the latest release, a clone and build, or the hosted URL.
The same server runs at https://mcp.zovo.one/mcp/onboarding over MCP streamable HTTP, no install. Mint a free token with curl https://mcp.zovo.one/mcp/token, or use a Pro key. It has no filesystem, so a file comes back as a one-hour download link.
{
"mcpServers": {
"onboarding": {
"url": "https://mcp.zovo.one/mcp/onboarding",
"headers": { "Authorization": "Bearer <token>" }
}
}
}
The current field table marks `type` as required, with `stdio` for a locally launched server, so write it out rather than relying on command and args alone. The other documented restriction is that `envFile` is stdio-only: a remote HTTP or SSE server does not read it, and its headers belong in the config.
Free: Every tool is free for one hire at a time: add, list, tasks, done, one-hire template apply, progress and overdue. Up to 500 rows on every list on every tier. Pro is $19 once, verified offline.
<project>/.cursor/mcp.json applies to that project and can be committed, which suits a server tied to one client. ~/.cursor/mcp.json applies everywhere. Both are managed from the Customize page.
The current field table marks type as required, with stdio for a locally launched server, so include it. Pointing at a remote endpoint, envFile is documented as stdio-only and is not read.
Servers in Cursor's marketplace get an Add to Cursor button. The deeplink reference currently documents prompt, command and rule links only, so for MCP Onboarding pasting the config block above is the supported route.
MCP Onboarding in detail · The same server in Claude Code and VS Code · Every server in Cursor · Guides · Cursor docs · Buy Pro