Allows the fetching of skill documentation and repository content directly from GitHub repositories to provide AI agents with immediate access to community-made instructions and code patterns.
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-master-mcp find and read a skill for converting markdown to PDF"
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.
A Plug & Play MCP server that connects your AI coding agent to the SkillsMP marketplace - 8,000+ community-made skills.
You can search for skills, easily install them (to ~/.claude/skills/) or read them directly into your agent's context (without installing).
No API key needed.
One command to set up.
The key idea is to help lazy people like me to use skills more often, and save time and tokens for our dear agents.
Related MCP server: SkillFlow MCP Server
Here’s a real use case: converting a Markdown file to PDF.
You can either have the agent learn how to do it via web search, or simply import the skill.
Super efficient and fast.
You: "I need to convert README.md to a PDF"
Agent: searches SkillsMP for "markdown to pdf"
→ finds a skill for it
→ reads the SKILL.md content from GitHub
→ now has the full instructions in context
Agent: "I found a skill for this. It uses Puppeteer to render
the markdown and save it as PDF. Let me do that now."
...converts your file using the skill's instructions.
You: ":))))"The skill was never installed to your ~/.claude/skills
The agent just read it, learned the approach, and executed it.
One-shot use.
If you want a skill permanently, you can install it too:
You: "Install that markdown-to-pdf skill for Claude Code"
Agent: runs install_skill
→ skill is now saved to .claude/skills/
→ available in every future conversationNo API key
No .env
No configuration
Just install and run
claude mcp add skills-master -- npx skills-master-mcpAdd to .cursor/mcp.json:
{
"mcpServers": {
"skills-master": {
"command": "npx",
"args": ["skills-master-mcp"]
}
}
}npx skills-master-mcpTool | Input | Output |
| keywords (e.g., | List of matching skills with name, author, stars, links |
| plain English (e.g., | Semantically relevant skills ranked by relevance |
| GitHub owner + repo + path | The skill's full SKILL.md content, loaded into agent context |
| GitHub source + skill names + target agents | Skill permanently saved to agent's skills directory |
| skill names | Deletes the skill files from agent's skills directory |
searchParameter | Type | Default | Description |
| string | required | Search terms |
| number |
| Page number |
| number |
| Results per page (max: 100) |
| string |
|
|
| string |
|
|
ai_searchParameter | Type | Default | Description |
| string | required | Natural language query |
| string |
|
|
read_skillParameter | Type | Default | Description |
| string | required | GitHub user/org |
| string | required | Repository name |
| string | — | Path to skill folder |
| string |
| Git branch |
install_skillParameter | Type | Default | Description |
| string | required | GitHub |
| string | required | Skill names (comma-separated) |
| string | required | Target agents (comma-separated) |
| boolean |
| Install globally (user-level) |
remove_skillParameter | Type | Default | Description |
| string | required | Skill names to remove (comma-separated) |
| string |
| Target agent |
| boolean |
| Remove from global scope |
Agent | Install | Remove |
Yes | Yes | |
Yes | Yes | |
Yes | — | |
Yes | — | |
Yes | — | |
Yes | — | |
Yes | — |
Your AI Agent
│
▼
skills-master-mcp (local, via npx)
├── search / ai_search ──▶ Proxy Backend ──▶ SkillsMP API
├── read_skill ──────────▶ GitHub (direct)
├── install_skill ───────▶ npx add-skill
└── remove_skill ────────▶ Local file deletionSearch requests go through a proxy backend so you don't need an API key. Everything else is direct.
Nothing to configure. Optional env vars for advanced use:
Variable | Default | Description |
| Production URL | Override backend endpoint |
|
|
|
|
| HTTP port (when |
MIT
Semantic search for skills using natural language queries. Powered by AI to understand intent.
Use this when keywords aren't enough - describe what you want to accomplish.
Parameters:
query: Natural language query (e.g., "How to build REST APIs with authentication")
Examples: "tools for web scraping", "help with React testing", "automate deployments"
Inputs: query (required), response_format.
Install skills from GitHub to AI coding agents.
Parameters:
source: GitHub "owner/repo" (e.g., "anthropics/claude-code") [REQUIRED]
skills: Skill names, comma-separated (e.g., "frontend-design,backend-dev") [REQUIRED]
agents: Target agents, comma-separated [REQUIRED] Valid: claude-code, cursor, codex, opencode, antigravity, github-copilot, roo
global: Installation scope [REQUIRED] true = user-level install to ~/.claude/skills (available across all projects) false = project-level install to ./.claude/skills (only this project)
Example: source="anthropics/claude-code", skills="frontend-design", agents="claude-code", global=false
Inputs: source (required), skills (required), agents (required), global (required).
Read skill file content (SKILL.md) from a GitHub repository. Use to preview a skill before installing.
Parameters:
owner: GitHub username/org (e.g., "anthropics")
repo: Repository name (e.g., "claude-code")
path: Path to skill folder (e.g., "plugins/frontend-design/skills/frontend-design")
branch: Git branch (default: "main")
If path has no skill.md, returns directory listing.
Inputs: owner (required), repo (required), path, branch.
Remove installed skills from an AI coding agent.
Parameters:
skills: Skill names to remove (comma-separated: 'skill1,skill2'). REQUIRED.
agent: Agent to remove from (default: 'claude-code') Valid: claude-code, cursor, codex, opencode, antigravity, github-copilot, roo
global: Removal scope [REQUIRED] true = remove from user-level ~/.agents/skills (global install) false = remove from project-level ./.agents/skills (project install)
Removes the skill directory and associated symlinks from the agent's skills directory.
Inputs: skills (required), global (required), agent.
Search SkillsMP marketplace for AI coding skills by keywords.
Parameters:
query: Search terms (e.g., "fastapi", "react testing")
page: Page number (default: 1)
limit: Results per page (default: 20, max: 100)
sort_by: "stars" (default) or "recent"
Returns skills with name, description, author, stars, and GitHub URL.
Inputs: query (required), page, limit, sort_by, +1 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Most tools have distinct purposes: ai_search and search both handle searching but differ in approach (semantic vs keyword-based), while install_skill, read_skill, and remove_skill clearly manage skill lifecycle. The overlap between ai_search and search creates minor ambiguity, but their descriptions help differentiate them.
Tools follow a consistent verb_noun pattern with snake_case throughout (ai_search, install_skill, read_skill, remove_skill, search). The only deviation is 'ai_search' versus 'search' where the prefix clarifies the semantic approach, maintaining overall readability.
With 5 tools, this server is well-scoped for managing AI coding skills. It covers core operations: discovery (two search tools), installation, inspection, and removal. Each tool earns its place without bloat, fitting typical server scope expectations.
The toolset provides strong coverage for skill management: discover, preview, install, and remove. A minor gap exists in updating or modifying installed skills, but agents can work around this by removing and reinstalling. Core workflows are well-supported.
Search & install 13,000+ AI agent skills from skills-hub.ai inside any MCP tool.
Find, read and install 50,000+ Agent Skills for Claude Code and other agents, with trust scores.
Agent skills for Claude, Codex and Cursor: find, install and load skills from one connector.
AgentPMT is the AI agent marketplace that turns any MCP-compatible AI assistant into an autonomous employee. Connect once and your agents gain access to a growing ecosystem of tools, workflows, and skills spanning communication, data analytics, development, file management, search, and more. AgentPMT dynamically discovers and orchestrates tools from across the MCP ecosystem, so your agents can independently find the right tool for any task without manual configuration.
