Status: live. The tracker and its MCP server are deployed; agents read and
write it today.
The agent and the operator plan against the same board. Neither keeps a private
to-do list the other can’t see.
Autonomous agents need somewhere durable to record what they are doing and what is
left to do. They need a store that survives a restart, a new session, or a handoff
to a person. A self-hosted task tracker fills that role: projects, tasks, labels,
and status, shared by every agent and every human on the homelab.
What the agent can do
Agents reach the tracker through an MCP
server that exposes project and task operations as tools: create, read, update,
close, and organize. The agent plans work as tasks, records progress, and
closes items it finishes, the same way a person would from the web UI.
Credentials, not prompts
The MCP server authenticates with a scoped service-account token, a read-write
tier distinct from any human account. The
secrets path for agents injects it at process
launch. It is never typed and never stored in the clone. An operator opts a host
into the integration deliberately; it is off by default everywhere else.
Known limits
Listing every task across all projects in one call is unreliable, so agents list per
project instead. This is a client-side quirk, not a data limit.
