Give Claude Code a real project queue, linked repository, card context, and a visible path from mission to review instead of managing work across terminal sessions.
Claude Code
Connected
Stellary
Launch workspace
Use Stellary Desktop when Claude Code should work in a local repository. Use the remote MCP endpoint when Claude Code should inspect or update live workspace objects as an MCP client.
01
Install and authenticate Claude Code on the machine that owns the repository.
02
Open Stellary Desktop and refresh the local runner catalog.
03
Attach the local Git folder to the matching Stellary project.
04
Select Claude Code as the agent execution target and launch a card mission.
05
Follow progress, questions, completion, or failure from Activity.
Mission STL-128
Install and authenticate Claude Code on the machine that owns the repository.
Checklist
Linked context
Run Claude Code on the connected machine in the repository linked to the Stellary project.
The local runner receives the mission and linked repository through the configured project. MCP offers a second path for interactive access to project objects and tools.
Run Claude Code on the connected machine in the repository linked to the Stellary project.
Keep the card, checklist, linked documents, rules, and expected outcome attached to the execution.
Progress, questions, cancellation, failure, and final output return to the mission Activity.
claude mcp add stellary \
--transport streamable-http \
https://api.stellary.co/mcp \
--header "Authorization: Bearer YOUR_TOKEN"The Desktop runner is the right path when Claude Code must inspect or modify files in a local Git repository. The machine remains the execution boundary and must be online, connected, and authorized for the workspace.
Link the repository to the project before launching the mission so the runtime does not have to guess which working tree belongs to the card.
The MCP connection is useful when Claude Code should list projects, read cards and documents, update allowed project objects, or participate as an external agent loop.
Use a personal access token for interactive work as yourself. Use an agent token when the runtime represents a dedicated Stellary agent with its own tool policy.
Local runner
Remote MCP
Primary job
Local runner
Work inside the linked repository.
Remote MCP
Operate on live Stellary project data.
Execution location
Local runner
Your connected desktop machine.
Remote MCP
Any compatible MCP client environment.
Identity
Local runner
Configured workspace agent and machine.
Remote MCP
Personal access token or agent token.
Best starting point
Local runner
Coding mission from a card.
Remote MCP
Explore projects or run an external agent loop.
Yes, through the connected Stellary Desktop runner when the target project has a linked local repository and the agent is configured for local execution.
No. Local missions use the Desktop runner. MCP is an additional route for direct access to Stellary workspace tools and queued external-agent workflows.
An offline, paused, or disconnected machine cannot claim a local mission. The workspace keeps the mission state visible instead of silently pretending execution started.
Workspace writes made with an agent token follow the agent autonomy policy. In approval mode, non-read tools become proposals for human review.
Connect the machine, link the repository, and keep the result in the project Activity.
Create a Stellary project