initLABSCO SUMMARY
The loop still needs a human hand on it.
Dependencies, priorities and continuous developer mode all work — a task unblocks when the one it depends on is approved, and the developer moves straight to the next item. What does not work autonomously yet is the loop itself: agents cannot schedule their own checks, so someone runs the status commands on the 120-second interval, and the maximum iteration count is 500. Automation scripts ship with the repository but need setup. Treat it as a project that is honest about being in progress.
What it is
An MCP server for AI-to-AI collaboration, designed so Claude and Gemini can work a project between them without a human relaying messages. State lives in JSON files on disk — tasks, missions, project state, plans, loop state and tickets — so both agents read the same board across sessions.
What you get
- A single entry point that loads existing context, resumes or creates the project plan, surfaces blockers and starts the work loop —
init - Directive creation from the CTO side, one at a time or batched, carrying priority and
dependsOnrelationships so tasks unblock automatically when their predecessors are approved —send_directive,send_batch_directives - The developer side: a priority-sorted view of assigned work, submission of completed tasks, and asynchronous questions when a spec is unclear —
get_all_tasks,submit_work,ask_question - Review and plan progression from the CTO side —
review_work,create_project_plan,update_plan_progress - Loop status for each agent, which is how continuous work mode is driven —
get_loop_status - A task status model of available, blocked, in_progress, in_review and completed, plus a ticketing system for bugs, enhancements and tech debt
Requirements
No account and no key. Clone the repository, run npm install, make src/index.js executable, then register it — a .mcp.json entry for Claude Code, or ~/.gemini/settings.json for Gemini. The package is ai-collab-mcp (1.0.0 in package.json).
Setup effort
Build from source — clone the repository, then follow the project's own run instructions
USE CASES
01
Starting a two-agent session from a cold start
Each agent runs the init call; existing context loads, the plan resumes or is created, and pending work is picked up rather than restarted.
02
Queueing a phase of work with real ordering
Batch the directives with priorities and dependencies, so the database connection task blocks the model task until it is approved.
03
Working through the queue without idling
Read the priority-sorted task list, submit each completed item, and continue straight to the next available one.
04
Resolving an ambiguous spec without a human
File the question against the task and let the reviewing agent answer it in the same board, then review the submitted work.
26 tools
Listed in project docs. Your client may show a different list.
startpingsend_directivesend_batch_directivesget_pending_tasksget_all_taskssubmit_worksubmit_reviewreview_workask_questionanswer_questioncreate_project_planupdate_plan_progressget_loop_statusget_autonomous_statusprocess_autonomous_actionget_contextupdate_contextupdate_project_stategenerate_handoffcreate_ticketget_ticketsupdate_ticketlink_ticket_to_missioncheck_mission_progressBEFORE YOU INSTALL
What to know first
Tools you get
26 tools named in the project's documentation.
Requires
- node on PATH
- node mcp-automator-v2
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
node .mcp-server/src/index.jsMCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"ai-collab": {
"command": "node",
"args": [
".mcp-server/src/index.js"
],
"cwd": "<YOUR_PROJECT_PATH>",
"env": {
"PROJECT_PATH": "<YOUR_PROJECT_PATH>",
"NODE_PATH": "<YOUR_PROJECT_PATH>/.mcp-server/node_modules"
}
}
}
}Gemini CLI
GEMINI CLI · JSON
{
"mcpServers": {
"ai-collab": {
"command": "node",
"args": [
"<YOUR_PATH_TO_AI_COLLAB_MCP>/src/index.js"
],
"env": {}
}
}
}
