skills-mcp
Related Servers
Alternatives to skills-mcp
- AlicenseAqualityCmaintenanceA package manager for AI agents that connects LLMs to a global registry of capabilities, allowing them to autonomously discover, install, and learn new skills from a centralized repository.43MIT
Related Servers
- AlicenseAqualityAmaintenanceA self-hostable semantic skill registry for AI agents, providing searchable, versioned, and verified skills over a single MCP endpoint with per-agent private vaults and trust tiers.7Apache 2.0
- AlicenseBqualityBmaintenanceA self-hosted registry and MCP server for reusable AI-agent skills that enables agents to discover, retrieve, and install skills with guardrails.57MIT
- FlicenseNot gradedqualityBmaintenanceA hierarchical MCP server for managing skill definitions with a browsable tree structure and full-text search. It allows AI agents to efficiently discover and use skills without consuming context tokens.-
- AlicenseNot gradedqualityBmaintenanceEnables centralized, versioned management and distribution of AI agent skills through a horizontally scalable MCP server, allowing agents to dynamically discover, search, and retrieve skills over HTTP/SSE.MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that makes Agent Skills available to any MCP-compatible agent through a declarative, package.json-based configuration, enabling team-shareable skill management and execution.4MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to discover, load, and recommend versioned skills from a self-hosted library over MCP, with scoped access and immutable revisions.13 npm213MIT
TDQS
Scored across 7 tools
Most tools are clearly distinct, with find_relevant/list_all for discovery and get_body/get_options for loading skill configuration. Some potential confusion exists between get_reference, get_asset, and run_script since all handle Tier 3 files, but the descriptions and two-phase list pattern help differentiate them.
All tools follow a consistent skills_ prefix with snake_case and a clear verb_noun structure (get_body, list_all, run_script, find_relevant). This makes the toolset predictable and easy to navigate.
Seven tools cover the full skill consumption workflow without redundancy or bloat. Each tool serves a distinct stage in the process, from discovery to loading instructions to fetching optional Tier 3 resources.
The toolset covers the complete lifecycle for consuming a skill: semantic search, browsing, loading instructions, optional configuration, references, assets, and script execution. No critical gaps are apparent for a skill-consumer-oriented MCP server.