claude-cockpit
MCP server for a kanban task board that lets Claude Code manage tasks with priority, categories, and multi-agent safety, plus a web UI for visual drag-and-drop.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
shmuelix
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
list_tasksList all Kanban tasks grouped by column. Optionally filter by category.
get_taskGet full details of a specific task by ID. Requires 'agent' param — will block details if another agent owns the task.
move_taskMove a task to a different column. Moving to in_progress requires 'agent' param and auto-claims the task. Fails if another agent already claimed it.
claim_taskClaim a task so no other agent can work on it. Fails if already claimed by someone else. Use this BEFORE moving a task to in_progress.
unclaim_taskRelease a claim on a task, making it available for other agents.
create_taskCreate a new task on the Kanban board. Cannot create directly into in_progress — use move_task after creating.
update_taskUpdate fields on an existing task. To change columns, use move_task instead.
add_noteAdd a note to a task.
delete_taskPermanently delete a task from the Kanban board.
fetch_calendarFetch Snooze app calendar feed and return NEW events not yet on the board. Review the results and use create_task to import only project-related items (skip personal errands, appointments, shopping, etc).
snooze_list_tasksList Snooze app tasks from Firestore. Returns active tasks by default.
snooze_create_taskCreate a new task in the Snooze app.
snooze_update_taskUpdate an existing Snooze app task.
snooze_delete_taskDelete a task from the Snooze app.
snooze_complete_taskMark a Snooze app task as completed.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
ws: Memory exhaustion DoS from tiny fragments and data chunks
esbuild allows arbitrary file read when running the development server on Windows
ws: Uninitialized memory disclosure
CALENDAR_FEED_URLoptional, for Snooze calendar importOPENAI_API_KEYrequired for AI auto-categorization of tasksTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
15/15 tools missing one or more hints — list_tasks (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_task (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); move_task (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +12 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 1 high severity in production deps — ws@8.19.0 (high), esbuild@0.27.3 (low)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/shmuelix/claude-cockpit)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check