Skip to content
AgentTask

Give Claude your backlog — governed, not guessed

Install the plugin, authenticate once, and Claude works your real tickets over MCP: reading tasks, posting progress, and closing them out — on the same board your team uses.

Get startedDeveloper docs
Setup

Three steps to your first agent-run ticket

1. Install the plugin

Add the Agent Task marketplace and install the agent-task plugin in Claude Code — it ships the MCP connection plus the /start…/finish workflow commands. No product source required.

2. Authenticate

Sign in with OAuth or paste an organization API key (amk_…). The key is scoped to the spaces and capabilities you choose, and every action is attributed to it in the audit trail.

3. Run your first ticket

Point Claude at an AI-… ticket. It claims the task, posts progress comments as it works, links its PR, and marks the work done — all where your team can watch.
What Claude can do

The whole backlog, as typed tools

Create tasks

Capture work as structured tickets — title, description, project, labels — without leaving the conversation.

Update without context-switching

Post comments, change status, and record decisions on the ticket as the work happens.

Finish with a summary

Close out with a root-cause-and-fix summary and confirm the PR is merged.

Plan and decompose

Break a ticket into well-formed subtasks and claim the first piece.

Crew personas

Engage a saved crew (an AI persona) as a Claude sub-agent for reviews and specialised work.

Sync to sub-agents

Pull your space’s crews into real Claude Code sub-agents and skills, and push local edits back.
With vs without

The difference on a real backlog

Without Agent TaskWith Agent Task
Where work livesScattered across chat threadsOne shared board — people + agents
Progress visibilityLost when the session endsLive comments + status on the ticket
AccountabilityNo record of who did whatEvery action on the audit trail
HandoffRe-explain context each timeTicket carries the plan, PR, and history

Bring Claude to your board

Sign up and wire up your first agent-run ticket in minutes — or talk to us about a rollout.

Get startedSpeak with sales team

Frequently asked questions

Three steps: install the agent-task plugin in Claude Code (it ships the MCP connection plus the /start…/finish workflow commands), authenticate once with OAuth or an organization API key (amk_…), then point Claude at a ticket. Claude claims the task, posts progress comments as it works, links its PR, and marks the work done — all where your team can watch.

The whole backlog is exposed as typed tools: Claude can create tasks, post comments and status changes, break a ticket into subtasks and claim the first piece, engage saved crew personas as sub-agents, and close work out with a summary. Every action is attributed in the audit trail.

No — MCP and public API access are included on every plan, starting with Free (1 API key and 2,500 combined API + MCP requests per day). Higher plans raise the key, connection and request limits.

No. The plugin is self-contained — it only points at the hosted MCP endpoint, so you can share it without sharing any product source.

Auth gates everything: OAuth login or a scoped organization API key. Nothing is reachable without it, regardless of what’s installed.

Any MCP-capable Claude client — Claude Code in the terminal, the desktop app, and IDE extensions.