tianshu-mcp
Related Servers
Alternatives to tianshu-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceEnables orchestrating external AI agents to execute development tasks with asynchronous management, automated acceptance verification, failure rework loops, and optional visual baseline validation.1118 npmApache 2.0
- AlicenseAqualityBmaintenanceEnables AI agents to delegate complex coding tasks, refactorings, and automated code reviews to OpenAI Codex and Google Antigravity CLIs, running them autonomously in YOLO mode with process supervision.6MIT
- AlicenseCqualityBmaintenanceEnables multiple CLI-based AI agents to collaborate as a coordinated team through shared task queues, shared memory, and a message bus, with DAG orchestration, rate-limit avoidance, parallel dispatching, and long-task management.633MIT
- AlicenseNot gradedqualityBmaintenanceEnables Codex or Claude Code to orchestrate persistent Antigravity CLI workers as independent implementers and testers within restricted workspace roots. It supports asynchronous task dispatch, progress polling, result inspection, follow-up messages, and cancellation with bounded, audited local event logging.5MIT
- AlicenseNot gradedqualityCmaintenanceCoordinates parallel AI coding agents by providing task ownership, scoped file locks, handoffs, and verification workflows.MIT
- AlicenseBqualityBmaintenanceEnables Codex to delegate frontend development, general implementation, and writing tasks to Gemini agents through task orchestration and dedicated writing tools, with opt-in file write and native tool permissions. Tasks are supervised across MCP disconnections, allowing progress polling, follow-ups, and explicit interruption.146MIT
TDQS
Scored across 8 tools
Most tools have sharply distinct roles: run_task creates work, wait_task blocks, verify_task audits, and the two visual-baseline tools are clearly paired. The one real overlap is query_info vs query_task — both 'read task state', with query_info(type=tasks/report) also touching task listing and reports that query_task seems adjacent to. manage_task's multi-action design (cancel/continue/rework) is internally differentiated by the action parameter but is a lot of behavior behind one name.
All eight names follow snake_case verb_noun (run_task, verify_task, wait_task, prepare_visual_baseline, approve_visual_baseline), which is predictable. The deviation is query_info, a generic bucket name that breaks the resource-specific *_task pattern and sits awkwardly next to query_task. Within-tool parameter naming (action=, type=) is consistent with the consolidation approach.
Eight tools is well within a healthy range for an agent-dispatch/verification server, and the authors clearly consolidated rather than proliferated. The tradeoff is that manage_task and query_info are each effectively 3 tools in one, pushing complexity into parameter space rather than the tool list. Slightly heavy per-tool surface, but the count itself is appropriate.
The lifecycle is well covered: dispatch, monitor (query_task events/logs), wait, verify, recover (cancel/continue/rework), historical listing and report retrieval, plus a visual-baseline approval flow. Gaps are minor but real — no way to delete/archive tasks or fetch dryRun plan/report artifacts directly, and agent/model capability discovery is only partially exposed via query_info(type=profiles).