coding-os
Related Servers
Alternatives to coding-os
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceLocal MCP server for Claude Code providing persistent memory, task planning, and agent coordination with full transparency and no network calls.2MIT
- AlicenseNot gradedqualityAmaintenanceA 68-tool MCP server providing persistent memory, error tracking, decision logging, task orchestration, and multi-modal AI generation for coding agents like OpenCode and Claude Code.MIT
- AlicenseCqualityDmaintenanceMCP server for sharing source-backed engineering memory across AI coding clients like Cursor and VS Code.301MIT
- AlicenseAqualityBmaintenanceMCP server for orchestrating coding tasks with frontier-model planning and local execution, enabling manifest validation, plan submission, status checks, cancellation, and report retrieval through Claude Code.6MIT
- FlicenseNot gradedqualityDmaintenanceMCP server that exposes local agents as tools for Claude Code, enabling capabilities in quant, trading, news, reports, robotics, Notion, and FreeCAD.13 npm1-
- AlicenseAqualityDmaintenanceThis MCP server enables remote control and management of Claude Code agents, allowing you to execute missions, configure agent personalities, and integrate with other MCP tools.79 npm1MIT
TDQS
Scored across 87 tools
The tools are grouped by domain with detailed descriptions that explicitly steer usage, but the sheer number of overlapping graph, search, and supervision tools creates real ambiguity. Pairs like cos_graph_diff/cos_graph_detect_changes, cos_graph_query/cos_graph_resolve, and cos_task_reclaim/cos_task_reconcile require careful reading to avoid misselection.
All tools share the cos_ prefix and use snake_case, and domain prefixes like graph_, task_, and doc_ provide useful structure. However, the suffix pattern is mixed: some names are verb-oriented (cos_graph_query, cos_task_create), some are noun-oriented (cos_graph_cycles, cos_graph_doctor), and some use inconsistent word order (cos_work_log_append, cos_digest_regenerate).
87 tools is an extreme count for any MCP server surface and far exceeds the typical well-scoped 3-15 tool range. Even with broad 'coding OS' ambitions, this volume will create significant selection overhead and cognitive load for agents.
The set provides unusually deep coverage across task lifecycle, graph analysis, memory, retrieval feedback, metrics, supervision, and trajectory tracking. Minor gaps exist—such as no explicit task archive/delete, no doc write/update tool, and cos_promote returning content without writing it—but most are workaroundable or outside the server's apparent read/analyze focus.