Checklists you build once and run many times, and the dated record of each run that somebody signs. You hold a checklist as a named list of steps, optionally grouped into sections, each required or optional, and run it against a job as many times as you like. A run marks every step pass, fail or not applicable, with who marked it, on what day, and a note saying what was found, and run_sign_off puts a name and a date on it and freezes it. A run COPIES its checklist's steps when it starts and records the version it copied, so editing the checklist afterwards never changes a run already under way and deleting the checklist leaves every run readable and complete. Not applicable counts as answered and never as passed: pass plus fail plus na plus pending equals the item count, and answered plus pending equals it too, which only both hold if na sits on the answered side. A required step unanswered or failed blocks the signature; force signs anyway and the exceptions stay on the record and print on the report. No count is stored: every figure is derived on the call, and a signed-off run cannot be edited or deleted, because it is the record of what somebody put their name to.
run_status, run_list, checklist_list and run_report as text are reads and safe to auto-approve. Keep run_check behind a click, because it writes who answered what, keep run_sign_off behind one because a signature is forever, and keep run_report with out_path behind one on any tier, because writing a file at a caller path is the one surface that touches the disk outside the store.
| You say | Tool |
|---|---|
| Make a pre-delivery vehicle check: tyre pressures, lights, load secured, weight within the plated limit. | checklist_create then checklist_item_add |
| Start a run for van BX21 KLM against WO-2026-0044. | run_start |
| Ben found the load at 3620 kilos against a plated 3500, that one fails. Can I sign it off? | run_check then run_sign_off |
On the worked pre-delivery run the steps answer pass, pass, na, pass, fail, pending: five of six answered, three pass, one fail, one not applicable, one pending. That run is not signable on two counts, a required step failed and an optional one is unanswered, and run_sign_off says both rather than only that the run is open. The contract suite asserts the snapshot rule on the raw runs.json bytes, not only through the API.
The file is mcp.json, and the key inside it is mcpServers.
| Scope | Path |
|---|---|
| Cline CLI | ~/.cline/mcp.json |
| The editor extension | opened from the Cline panel, not by path; the documentation deliberately calls it the MCP settings JSON used by the extension |
If you also run Claude Desktop, the shortest path there is one click: checklist.mcpb
from the latest release opens as an extension, with no JSON and no terminal.
Cline reads its own config, so here it is:
The config block:
{
"mcpServers": {
"checklist": {
"command": "node",
"args": ["/absolute/path/to/mcp-servers/servers/checklist/dist/index.js"],
"disabled": false,
"autoApprove": []
}
}
}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/checklistThat writes servers/checklist/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": {
"checklist": {
"command": "npx",
"args": ["-y", "@theluckystrike/mcp-checklist"]
}
}
}No full-app restart. The MCP settings actions include restarting an unresponsive server if its tools do not appear.
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/checklist 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.
Write the transport in. Omitting type falls back to the legacy sse transport, which will not talk to this endpoint:
{
"mcpServers": {
"checklist": {
"type": "streamableHttp",
"url": "https://mcp.zovo.one/mcp/checklist",
"headers": { "Authorization": "Bearer <token>" }
}
}
}Cline is the one client here with an unsafe transport default. `type` selects it, and omitting `type` falls back to the legacy sse transport, so a streamable HTTP endpoint needs it written in or you will debug a server that is fine. Local entries carry "disabled" and an "autoApprove" array.
Free: Three checklists, and unlimited runs of them on every tier, because capping the running of a checklist would cap the only thing a checklist is for. Up to 500 steps on a checklist on every tier. Every read, every count, the failures, the outstanding list and the run report text are free, and deleting a checklist frees its slot. Pro is $19 once, verified offline.
The CLI reads ~/.cline/mcp.json. For the extension, do not hunt for a path: MCP Servers icon, Configure tab, Configure MCP Servers. cline mcp opens a wizard, and cline config mcp --json is the non-interactive form.
Set the transport explicitly. Omitting type falls back to the legacy sse transport, so streamable HTTP needs "type": "streamableHttp" written in. It is the one default here that sends you debugging a server that works.
Approve the read-only ones and leave the writing ones behind a click: each entry carries an autoApprove array and a disabled flag.
MCP Checklist in detail · The same server in Windsurf and Claude.ai and Claude Desktop connectors · Every server in Cline · Guides · Cline docs · Buy Pro
Work orders and job cards from chat, and why the markup goes on the unit cost