A
licenseNot graded
qualityA
maintenanceEnables Claude Code to launch and supervise multiple concurrent Claude Code sessions in tmux, sending them briefs, reading their progress, answering their prompts, and managing isolated git worktrees.
2
MIT
multi-agent-mcp
by shiiman
Related Servers
Alternatives to multi-agent-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceCreates and manages multi-agent teams of AI coding assistants (Claude Code, Codex CLI) that collaborate in tmux terminal sessions. Enables a leader agent to assign sub-tasks to team members for coordinated development.ISC
- FlicenseAqualityDmaintenanceEnables AI agents to spawn, interact with, and orchestrate multiple concurrent terminal sessions via tmux.9-
- AlicenseAqualityDmaintenanceOrchestrates multiple Claude Code agents across iTerm2 sessions with process-level isolation, enabling collaborative AI development workflows on multiple codebases with task-based inter-agent communication and persistent state management.71MIT
- AlicenseNot gradedqualityCmaintenanceEnables Claude Code to orchestrate a team of independent Claude Code sessions within iTerm2 for parallel task execution and isolated git worktree management. It provides tools to spawn, monitor, and message worker sessions while maintaining full visibility and control over their terminal windows.49MIT
- AlicenseCqualityBmaintenanceEnables delegating coding tasks to multiple AI CLI agents (Claude Code, Antigravity, Codex, Cursor) with session memory and diff inspection.1618 npmMIT
TDQS
C2.9/5.0
Scored across 90 tools
Disambiguation3/5
Many tools have clear distinct purposes, but there is significant overlap in areas like task management (create_task, enqueue_task, assign_task_to_agent, send_task) and memory retrieval (retrieve_from_memory, search_memory_archive, get_memory_entry). Also cleanup_workspace and cleanup_on_completion overlap, and check_gtr_available/check_gtrconfig are confusingly similar.
Naming Consistency4/5
Most tools follow a consistent verb_noun pattern (get_, list_, create_, update_, delete_, remove_, send_, etc.). Minor deviations exist such as 'merge_completed_tasks' (verb_adjective_noun) and 'monitor_and_recover_workers' (compound verb) but these are understandable.
Tool Count1/5
90 tools is an extremely high count. Even for a multi-agent orchestration system, this is far beyond what an agent can reasonably navigate. The count is justified by the breadth of the domain, but it represents a severe cognitive load and should be split into multiple focused servers.
Completeness4/5
The domain coverage is remarkably thorough: agent lifecycle, task lifecycle, worktree management, messaging, memory, health checks, screenshots, cost tracking, and model profiles. Minor gaps include no explicit update_agent or update_worktree tools, but most operational cycles are complete.
Maintenance
ActivityStale
ResponsivenessUnresponsive