@skills-hub-ai/mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@skills-hub-ai/mcp what skills do I have installed?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@skills-hub-ai/mcp
MCP server for skills-hub.ai — serve your installed skills as prompts in Claude Code, Cursor, or any MCP-compatible tool.
Setup
Claude Code
claude mcp add skills-hub -- npx @skills-hub-ai/mcpCursor
Add to your Cursor MCP settings (~/.cursor/mcp.json):
{
"mcpServers": {
"skills-hub": {
"command": "npx",
"args": ["@skills-hub-ai/mcp"]
}
}
}Manual (any MCP client)
{
"command": "npx",
"args": ["@skills-hub-ai/mcp"]
}Related MCP server: Skillz
How It Works
The server scans these directories for installed skills:
Tool | Directory |
Claude Code |
|
Cursor |
|
Each skill directory should contain a SKILL.md file (installed via skills-hub install <slug>).
Skills are exposed as MCP prompts — your AI tool can list and invoke them. The server caches discovered skills for 30 seconds.
Installing Skills
Use the CLI to install skills:
npx @skills-hub-ai/cli search "code review"
npx @skills-hub-ai/cli install <skill-name>Links
Available Tools
4 toolsget_skill_detailBInspect
Get full details about a skill including instructions, composition children, and metadata. The result includes a url to the skill's page on skills-hub.ai; show that link to the user.
Inputs: slug (required).
install_skillBInspect
Install a skill from skills-hub.ai to the local skills directory
Inputs: slug (required), target.
list_installed_skillsBInspect
List all locally installed skills
Inputs: no named parameters.
search_skillsAInspect
Search the skills-hub.ai catalog for skills matching a query. Supports org-scoped search to include organization-private skills (requires SKILLS_HUB_API_TOKEN). Each result includes a url to the skill's page on skills-hub.ai; show that link to the user alongside each skill you mention.
Inputs: query (required), limit, category, organization.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool maps to a distinct resource+action pair: catalog search, catalog detail lookup, local inventory listing, and installation. There is no plausible confusion between remote catalog reads and local-state operations.
All four tools use consistent snake_case verb_noun naming (search_skills, get_skill_detail, list_installed_skills, install_skill). The verb choice (search/get/list/install) accurately signals the action in each case.
Four tools is small but appropriate for a focused catalog-plus-installer client; each tool earns its place with no filler. It leans slightly thin, since a couple of lifecycle operations are absent.
The core flow (search → inspect → install, plus listing what is installed) is fully covered with no dead ends. Minor gaps remain: no uninstall/remove tool, no update/upgrade for installed skills, and no way to read an installed skill's local instructions.
Maintenance
Related MCP Connectors
Agent skills for Claude, Codex and Cursor: find, install and load skills from one connector.
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Governed AI agent skills — one library, distributed to devs and exposed to remote agents over MCP.
Hosted MCP server for live public-data APIs and Skills for AI agents.
Related MCP Servers
- AlicenseAqualityDmaintenanceConverts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.339 PyPI30Apache 2.0
- AlicenseNot gradedqualityDmaintenanceTurns Claude-style skills (SKILL.md files with resources) into callable MCP tools for any agent. Discovers skills from a directory, exposes their instructions and resources, and can execute bundled helper scripts.118 PyPI410MIT
- AlicenseNot gradedqualityNot gradedmaintenanceAn MCP server that transforms Claude-style skills and resources into callable tools for any MCP-compatible agent or client. It automatically discovers, exposes, and executes scripts from skills organized in local directories or packaged archives.MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that adapts, activates, and shares local Agent Skills for runtimes like OpenAI Agents SDK and Claude Code, enabling dynamic discovery and shareable HTML/image artifacts.40 npm3MIT