A
licenseA
qualityB
maintenanceAn MCP server that lets OpenAI Codex delegate tasks to Google Gemini agents as isolated background workers, with Git worktree isolation, loop detection, and security boundary enforcement.
7
1
MIT
sol-luna-orchestrator
by mahadansar
Related Servers
Alternatives to sol-luna-orchestrator
No user-submitted related servers found.
Related Servers
- AlicenseAqualityCmaintenanceAn MCP server that splits coding work between ChatGPT web (planning, review) and Codex CLI (implementation), enabling agentic workflows over a local repo with risk-gated execution and safety rails.23MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that lets Codex supervise Claude Code or DeepSeek Harness as workers in isolated Git worktrees, with a bridge_run/bridge_respond/bridge_apply workflow for task delegation and safe cherry-pick integration.5 npmApache 2.0
- AlicenseNot gradedqualityAmaintenanceA local MCP server that enables Codex and other MCP clients to orchestrate native external coding-agent harnesses through a normalized lifecycle, with guarded execution and deterministic testing.248 PyPIMIT
- AlicenseAqualityDmaintenanceA local MCP server that lets Claude delegate scoped work to Codex with structured results and guardrails, supporting planning, code review, build, reverse engineering, and long-running background tasks.11MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that bridges Codex with DeepSeek Harness to delegate coding tasks into isolated worktrees, providing profile-based model routing, single/multi-agent orchestration, and reviewable artifacts.14 npm1Apache 2.0
TDQS
A4.3/5.0
Scored across 5 tools
Disambiguation4/5
Each tool targets a distinct orchestration stage: cheap advisory routing_preflight, single-seam delegate_task, multi-seam delegate_tasks, same-thread continue_task, and read-only explore. The only real overlap is delegate_task vs delegate_tasks, which the descriptions resolve explicitly ('prefer delegate_task when no scheduling is needed'), so an agent can select correctly.
Naming Consistency4/5
Four tools follow a readable snake_case verb_noun pattern (continue_task, routing_preflight, delegate_task, delegate_tasks), though delegate_task/delegate_tasks differ only by pluralization. 'explore' breaks the pattern as a bare verb, and 'routing_preflight' is noun-flavored, but the set is still predictable.
Tool Count5/5
Five tools is well-scoped for a delegation orchestration server: one advisory check, two delegation paths, a continuation, and a read-only exploration mode. No tool looks redundant or bolted on.
Completeness4/5
The surface covers the core lifecycle: preflight gating, single and batch delegation, continuation, and exploration, with rich result/recovery semantics described. Gaps are minor — there is no explicit cancel or status/poll tool, and the descriptions assume agents remain silent while pending, so a parent cannot actively query in-flight work.
Maintenance
ActivityActive
ResponsivenessNo issues