135 tools — 4 production packages on PyPI

MCP tools that actually work.

A framework for building MCP servers.
And a growing catalog of production-ready tool packages.

$ pip install mcp-shell-tools
$ mcp-shell-tools
✓ MCP Shell Tools v4.0.2 — 26 tools, stdio ready

# Or use as a Python library
>>> from mcp_shell_tools.shell import tools
>>> tools.file_read("/etc/hostname")
'cirrus7'
135
Tools
4
PyPI Packages
Dual-Use
MCP + Python
0
Vendor Lock-in

One framework. One plugin interface.

Build MCP servers in minutes. Every tool package follows the same pattern.

Framework

mcp-server-framework

The foundation. Config loading, transport (stdio + HTTP), health endpoint, OAuth, plugin system. Everything you need to build an MCP server.

$ pip install mcp-server-framework
# Your plugin:
def register(mcp, config):
    @mcp.tool()
    def my_tool(x: str):
        return f"done: {x}"
Dual-Use

MCP Server + Python Library

Every tool package works as a standalone MCP server and as a regular Python library. No MCP required to use the functions.

# As MCP server
$ mcp-shell-tools

# As Python library
from mcp_shell_tools.shell import tools
result = tools.file_read("/etc/hosts")
Plugin System

One function. That's it.

Implement register(mcp, config). Add @mcp.tool() decorated functions. Your package works standalone and as a framework plugin.

# Claude Desktop config
{
  "mcpServers": {
    "shell": {
      "command": "mcp-shell-tools"
    }
  }
}

Every package follows the same pattern.

One interface. Standalone or plugin. MCP server or Python library.

01

Install

Each tool package is on PyPI. One pip install, ready to use.

$ pip install mcp-shell-tools
$ mcp-shell-tools
✓ 26 tools, stdio ready
02

Use as library

Every tool works as a Python function. No MCP needed.

from mcp_shell_tools.shell import tools

result = tools.file_read("/etc/hosts")
files = tools.glob_search("**/*.py")
03

Build your own

The framework handles transport, config, health. You write the tools.

def register(mcp, config):
    @mcp.tool()
    def greet(name: str):
        return f"Hello, {name}!"

Build your own in minutes.

One function. That's the entire plugin API.

# my_tools/__init__.py

def register(mcp, config: dict) -> None:
    """Register your tools as MCP tools."""

    @mcp.tool()
    def greet(name: str) -> str:
        """Say hello."""
        return f"Hello, {name}!"

    @mcp.tool()
    def add(a: int, b: int) -> str:
        """Add two numbers."""
        return str(a + b)

# That's it. Works standalone and as a framework plugin.

Common questions.

"Can I use a tool package without the framework?"

Yes. Every package exports pure Python functions. Import and call directly — no MCP, no server, no overhead.

"How do I build my own tool package?"

Implement register(mcp, config). That's the entire API. Add @mcp.tool() decorated functions inside. Your package works standalone and as a framework plugin.

"Does it work with Claude Desktop / Claude Code?"

Yes. Every tool package runs as a stdio MCP server. Add it to your Claude Desktop config and it just works.

"What Python version do I need?"

Python 3.10 or newer. All packages are tested on 3.10, 3.11, and 3.12.

Production-ready MCP tools.

Each package works standalone or as a framework plugin. Install, run, done.

mcp-shell-tools

26 tools — Filesystem, editor, search, shell, system diagnostics. The workstation toolkit for AI agents.

pip install mcp-shell-tools

mcp-homematic-tools

60 tools — HomeMatic CCU3 / OpenCCU smart home. Full JSON-RPC API coverage: devices, channels, rooms, programs, system variables.

pip install mcp-homematic-tools

mcp-playwright-tools

43 tools — Browser automation. Navigation, interaction, content extraction, screenshots, semantic locators.

pip install mcp-playwright-tools

mcp-image-tools

6 tools — Image processing. Read, resize, crop, convert, screenshot. Base64 output for direct use in LLM context.

pip install mcp-image-tools
Browse on GitHub

Start building.

$ pip install mcp-server-framework