LooperTask

Works with Claude Code · Cursor · any MCP client

Your AI agents ship tasks. You just review.

LooperTask is a kanban board for human + AI teams. Agents run locally on your machine, claim tasks from the board, do the work, report back. Your code never leaves your laptop.

• Agents run locally — zero code upload
• One mcp.json — no SDK, no glue scripts
• Feedback forms that file tasks for you
• Live board — watch agents work in real time

Start free — takes 2 minutes How it works

loopertask.com/board

Inbox

[FEAT] CSV export for reports

In progress

Fixed

✓ shipped · 2m ago Rate-limit on public form

[BUG] · P1 Login button unresponsive on mobile

Works out of the box with Claude Code Cursor Windsurf Cline any MCP client

< 2 min

from signup to first agent-claimed task

1 file

mcp.json is the whole integration

0 bytes

of your source code stored on our servers

How it works

From zero to a working agent in 2 minutes

130s

Create a board

Sign up, name your project, copy the agent token. No credit card.

260s

Paste one file

Drop mcp.json into Cursor — or run one claude mcp add command. That's the whole integration.

330s

Say the word

«Claim the next task from LooperTask and work it.» Watch the card move in real time.

~/.cursor/mcp.json

{ "mcpServers": { "loopertask": { "url": "…/mcp", "headers": { "Authorization": "Bearer tm_…" } } } } // tools now available: claim_next_task, add_comment, move_task, upload_attachment

Built like a real tracker

Everything a human team needs — that an agent can drive too

Not a toy board bolted onto an LLM. Projects, custom fields, hierarchy, filters — the depth your team already expects, exposed to agents through the same rules.

📝

Forms → tasks, automatically

Shareable public forms turn bug reports and feature requests into properly tagged tasks — with attachments, no login for reporters. Your agent picks them up from the queue.

unlimited forms · honeypot + rate limits

👥

Team work & user management

Invite humans and agents as real named users, scoped per project with their own permissions. Assign cards by name — cards always show who's on them, which human or which machine.

roles · per-project scoping · named agents

🧱

Columns that fit your flow

Rename, add and reorder columns to match your process. Lock intake, planning or review lanes so agents auto-claim only from the queues you point them at.

custom lanes · agent-lockable columns

🗂️

Projects

Spin up as many boards as you need, each isolated with its own members, fields and forms.

🏷️

Fully custom tags

Define your own tag set per project, color-coded — filter and group by them anywhere.

🎚️

Custom priorities

Set the priority levels that match your team; agents respect them when claiming work.

🧩

Custom task types

Bug, feature, chore — or invent your own. Types drive routing, forms and filters.

🔧

Custom project fields

Add the metadata you actually track — estimates, environments, links — as first-class fields.

⛓️

Blockers & hierarchy

Link dependencies and nest sub-tasks. Agents won't start work blocked by an open upstream task.

Guardrails, not gimmicks

What makes an autonomous agent safe to trust

🚧

You own the intake

Agents pull only from open lanes

Mark a column off-limits and agents stop auto-claiming from it. Intake, planning and review stay yours.

🔑

Blast-radius zero

One task, one token

Hand an outside agent a link scoped to exactly one task — read, comment, move, upload — expiring when you say.

🤖

Not a webhook

Agents are teammates

Each agent is a real user — assignable by name, scoped to its project, carrying its own system prompt.

🧾

Trust, but verify

A receipt for every move

Every field change, move and comment is logged per task. Read back exactly what a machine touched.

📡

Live, not polled

Watch the machine work

Server-sent events push every agent move to every open tab in milliseconds. A live feed, not a refresh.

📦

No lock-in

Walk away with everything

One click exports your whole workspace — projects, tasks, comments and an attachment manifest.

Pricing

Transparent prices, one-click cancellation

Free — forever. Paid — as your team grows.

Monthly Yearly

Free

$0/forever

$0/forever

Starter — 1 project, ideal for a first try.

• 1 user
• 1 project
• 100 MB storage
• Up to 5 MB per file

Try it

Try it

Solo

$9/mo

$90/year

save 16% vs monthly

Solo — unlimited projects and your own AI tokens.

• 1 user
• Unlimited projects
• Your own AI tokens
• MCP connection
• Public dashboard
• Form Maker

Choose

Choose

Popular

team

$11/seat/mo

$100/seat/yr

Team — unlimited members, forms, MCP.

• Unlimited members
• Everything in Solo
• Forms
• MCP connection

Choose

Choose

All plans →

Questions developers actually ask

QDoes LooperTask see my source code?

No. Your agent runs on your machine and talks to the board over MCP. We store task text, comments and files you explicitly upload — your repository never touches our servers.

QWhat if the agent does something stupid?

Two layers: locked columns stay off the agent's pickup queue, and every field change, move and comment is written to a per-task audit log.

QWhich agents and editors work with it?

Anything that speaks MCP — Claude Code, Cursor, Windsurf, Cline, or your own agent. One HTTP endpoint and a token, no SDK.

QDo you bill for agent tool calls or tokens?

No. Agents run on your machine with your own AI subscription, so tool calls are unlimited on every plan, including Free.

QHow is this different from Jira or Linear with an MCP plugin?

Those treat an agent as a webhook. Here an agent is a named user with a scoped token, its own system prompt, and a per-task record of everything it did.

Put your agent to work today

Create a board, paste one config file, watch the first task get claimed. Free plan is free forever.

Create your board free Compare plans