Access 1200+ AI Agent tools via Model Context Protocol (MCP)
npx skills add https://github.com/claude-office-skills/skills --skill mcp-hub
This skill provides access to 1200+ MCP (Model Context Protocol) servers - standardized tools that extend AI capabilities. Connect Claude to filesystems, databases, APIs, and document processing tools.
Example prompts:
Claude ←→ MCP Server ←→ External Resource
(Protocol) (Files, APIs, DBs)
| Server | Function | Stars |
|--------|----------|-------|
| filesystem | Read/write local files | Official |
| google-drive | Access Google Docs/Sheets | 5k+ |
| puppeteer | Browser automation, PDF gen | 10k+ |
| sqlite | Database queries | Official |
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/path/to/documents"
]
},
"google-drive": {
"command": "npx",
"args": ["-y", "@anthropic/mcp-google-drive"]
}
}
}
Browse available servers:
# MCP tools become available to Claude automatically
# Example: filesystem MCP provides these tools:
# read_file(path) - Read file contents
# write_file(path, content) - Write to file
# list_directory(path) - List directory contents
# search_files(query) - Search for files
# Install required dependencies
pip install python-docx openpyxl python-pptx reportlab jinja2
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Take claude-office-skills/mcp-hub from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.