phases-agents
Related Servers
Alternatives to phases-agents
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceA local, read-only MCP server that lets coding agents search the complete AAS skill catalog, compose and validate agent-chosen skill stacks, and generate reproducible, reviewable plans without uploading project code.3,212 npm1MIT
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to search, recommend, and validate a stack of reusable skills from a local catalog, producing deterministic plans without modifying the project.3,212 npm1MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to search a local catalog, load skills, inspect MCP tool schemas, and invoke selected tools through a single unified MCP tool, reducing per-request overhead.1MIT
- FlicenseNot gradedqualityBmaintenanceEnables multi-step, opinionated workflows (skills) as MCP resources with lazy loading, encoding team knowledge like branch naming and test procedures alongside tool execution.2-
- AlicenseNot gradedqualityBmaintenanceEnables AI clients to discover, search, retrieve, and read supporting files from a centrally published, versioned skill registry through four read-only MCP tools.1,505 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to search, browse, install, and manage a large library of skills via only 7 MCP tools, with skills stored locally and loaded on demand to minimize context overhead.4-
TDQS
Scored across 5 tools
Each tool targets a distinct operation: detect (profile), get_skill (read one), list_skills (enumerate), refresh_skills (rebuild registry), plan (produce a plan). The one soft overlap is that plan already performs detection, so an agent might wonder when to call detect versus plan directly.
All tools share the consistent phases_agents_ prefix followed by clear snake_case verbs/verb_noun forms (detect, get_skill, list_skills, plan, refresh_skills). No mixing of conventions.
Five tools is well-scoped for a skill-registry/planning domain, covering discovery, retrieval, detection, planning, and registry refresh without redundancy.
The surface covers the full read-side lifecycle: enumerate skills, read a skill, refresh the registry, detect a target, and produce a plan. It is read-only by design (no skill authoring/editing), which is a minor gap but consistent with the stated bounded-execution purpose.