skill-mcp
Related Servers
Alternatives to skill-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables MCP clients to discover, search, and load agent skills from many sources, including other agents' skill directories, Claude Code plugin marketplaces, and remote git repositories, with no copying or syncing required.1,309 npm6MIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP-capable agents to search, inspect, lint, and safely install Agent Skills from the skillmd registry mid-conversation.16 npm1MIT
- 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-
- AlicenseNot gradedqualityBmaintenanceEnables 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
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to keep skill catalogs outside the main LLM context and load only task-relevant SKILL.md instructions via a single MCP tool, reducing context overhead.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to discover, install, and manage SKILL.md skills from a Git-backed registry via MCP tools for search, install, and list operations.23 npm1MIT
TDQS
Scored across 12 tools
Most tools address distinct actions: binding, listing, suggesting, rescanning, archiving, reading, and estimating. A few diagnostic/inspection tools (doctor, list_skills, get_binding, why) have some overlapping concerns, but their descriptions make each purpose clear enough.
Most tools follow an imperative verb_noun pattern like bind_skills, list_skills, rescan_skills, and estimate_tokens. A few names deviate (doctor, why, native_skills_bypass), but the pattern is still predictable overall.
Twelve tools is a well-scoped set for a skill-management server. Each tool covers a distinct part of the workflow: cataloging, binding, suggesting, diagnosing, archiving, reading, and host integration, without obvious bloat.
The tool surface covers core lifecycle needs: listing, reading, binding, suggesting, rescanning, archiving, and host contract writing. Restoring archived skills or configuring skill roots is not directly exposed, but those feel like external/recoverable edge cases rather than critical gaps.