by getfounded
Agentic abstraction layer for building high precision vertical AI agents written in python for Model Context Protocol.
# Add to your Claude Code skills
git clone https://github.com/getfounded/mcp-tool-kitLast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T16:37:48.192Z",
"npmAuditRan": true,
"pipAuditRan": false
}mcp-tool-kit is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by getfounded. Agentic abstraction layer for building high precision vertical AI agents written in python for Model Context Protocol. It has 109 GitHub stars.
Yes. mcp-tool-kit passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/getfounded/mcp-tool-kit" and add it to your Claude Code skills directory (see the Installation section above).
mcp-tool-kit is primarily written in Python. It is open-source under getfounded on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh mcp-tool-kit against similar tools.
No comments yet. Be the first to share your thoughts!
A comprehensive toolkit for the Model Context Protocol (MCP) with automatic tool discovery and multiple transport options.
📚 Official Documentation | 🌐 Website | 💬 Community
🚀 Built by UsefulAI | 📖 From GitHub to Commercial Success
Choose your platform and run ONE command:
irm https://raw.githubusercontent.com/getfounded/mcp-tool-kit/main/install.ps1 | iex
bash <(curl -s https://raw.githubusercontent.com/getfounded/mcp-tool-kit/main/install.sh)
bash <(wget -qO- https://raw.githubusercontent.com/getfounded/mcp-tool-kit/main/install.sh)
That's it! The installer will:
Download the latest release:
Extract and run:
install.bat./install.shClone the repository
git clone https://github.com/getfounded/mcp-tool-kit.git
cd mcp-tool-kit
Run the launcher
launch.bat./launch.shdocker run -it --name mcp-toolkit ghcr.io/getfounded/mcp-tool-kit:latest
Tools are automatically discovered and registered at runtime - no manual configuration needed!
Control everything through a simple config.yaml file:
enabled_tools:
filesystem: true
time_tools: true
brave_search: true
# ... more tools
tool_config:
filesystem:
allowed_directories: ["~/Documents", "~/Downloads"]
brave_search:
max_results: 10
.env.template to .envBRAVE_SEARCH_API_KEY=your_key_here
NEWS_API_KEY=your_key_here
FRED_API_KEY=your_key_here
# ... other keys
MCP Tool Kit uses a dedicated storage directory for file operations:
C:\Users\{Username}\mcp-tool-kit-storage~/mcp-tool-kit-storageThe storage directory is automatically created when you first run the Docker container. You can also manually set it up:
Windows (PowerShell):
.\scripts\setup-storage.ps1
Mac/Linux:
./scripts/setup-storage.sh
mcp-tool-kit-storage/
├── documents/ # For document files
├── downloads/ # For downloaded files
└── workspace/ # For temporary work files
All file operations through the filesystem tool will be restricted to this directory for security.
{
"mcpServers": {
"mcp-tool-kit": {
"command": "docker",
"args": ["exec", "-i", "mcp-server", "python", "mcp_server_v2.py"]
}
}
}
http://localhost:8080/sse - Server-Sent Events stream/messages - Send messages to the serverTools now use a standardized base class system:
from app.tools.base_tool import BaseTool
class MyCustomTool(BaseTool):
def get_name(self) -> str:
return "My Custom Tool"
def get_tools(self) -> Dict[str, Callable]:
return {
"my_function": self.my_function
}
async def my_function(self, param: str, ctx: Context = None) -> str:
return f"Processed: {param}"
See the developer documentation for detailed guides.
Full documentation is available at https://docs.mcp-tool-kit.com.
To run documentation locally:
cd docsnpm installnpm startThe launcher scripts handle all Docker operations automatically.
# Start server
docker-compose up -d
# View logs
docker-compose logs -f
# Stop server
docker-compose down
# Rebuild after changes
docker-compose build --no-cache
app/tools/This project is licensed under the MIT License - see the LICENSE file for details.