Dedalus Python
A simple and performant Model Context Protocol framework for Python.
What is Dedalus Python?
Dedalus Python is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to simple and performant model context protocol framework for python.
A simple and performant Model Context Protocol framework for Python.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A simple and performant Model Context Protocol framework for
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx dedalus-mcp-pythonConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Dedalus Python
Dedalus MCP is a lightweight, spec-faithful Python framework for building Model Context Protocol servers and clients, weighing in at 137 KB compared to heavier alternatives. It provides decorators for registering tools, resources, and prompt templates, with built-in support for OAuth 2.1 authorization, DPoP token binding, StreamableHTTP transport with DNS rebinding protection, and MCP sampling. Python developers use it when they need a minimal, audit-friendly foundation to build custom MCP servers that integrate cleanly with their existing security infrastructure.
Prerequisites
- Python 3.12+ (the project uses `uv` with `--python 3.12`)
- uv package manager installed (`curl -LsSf https://astral.sh/uv/install.sh | sh`)
- An MCP client such as Claude Desktop for testing your server
- Optional: an OAuth 2.1-compatible identity provider if you need authenticated endpoints
Clone the repository
Clone the dedalus-mcp-python repository to get the framework source and examples.
git clone https://github.com/dedalus-labs/dedalus-mcp-python.git
cd dedalus-mcp-pythonInstall dependencies with uv
Use uv to create a virtual environment and install the project dependencies, targeting Python 3.12.
uv sync --python 3.12Create a simple MCP server
Create a Python file and define your tools using the `@tool` decorator, then register them with MCPServer and start it. The server listens on port 8000 with StreamableHTTP transport by default.
from dedalus_mcp import MCPServer, tool
@tool(description="Add two numbers together")
def add(a: int, b: int) -> int:
return a + b
@tool(description="Greet a user by name")
def greet(name: str) -> str:
return f"Hello, {name}!"
server = MCPServer("my-server")
server.collect(add)
server.collect(greet)
if __name__ == "__main__":
server.run()Run tests to verify the installation
Run the project test suite with pytest to confirm everything is working correctly before building your own server.
PYTHONPATH=src uv run --python 3.12 python -m pytestStart your MCP server
Run your server script. It will start on http://localhost:8000 using StreamableHTTP transport, ready to accept MCP client connections.
uv run --python 3.12 python my_server.pyConfigure Claude Desktop to connect
Add a stdio or HTTP entry in your Claude Desktop config pointing to your server. For local development with stdio, wrap the server start command.
{
"mcpServers": {
"dedalus-demo": {
"command": "uv",
"args": ["run", "--python", "3.12", "python", "/absolute/path/to/my_server.py"]
}
}
}Dedalus Python Examples
Client configuration
Claude Desktop config connecting to a locally running dedalus-mcp server via uv stdio.
{
"mcpServers": {
"dedalus-demo": {
"command": "uv",
"args": [
"run",
"--python",
"3.12",
"python",
"/Users/yourname/projects/my-mcp-server/server.py"
]
}
}
}Prompts to try
After connecting Claude Desktop to a server built with Dedalus MCP, test the registered tools.
- "Add 42 and 58 using the add tool."
- "Greet Alice using the greet tool."
- "List all available tools on the connected MCP server."
- "Call the [your-tool-name] tool with these parameters: ..."Troubleshooting Dedalus Python
Import error: 'No module named dedalus_mcp'
Make sure you run the server with `PYTHONPATH=src` or use `uv run` from the project root. The package source lives in the `src/` directory and must be on the Python path.
Server starts but Claude Desktop cannot connect
For local development, verify the absolute path in your config is correct and the uv binary is on your PATH. For HTTP transport, ensure no firewall is blocking port 8000 and the server is actually running before Claude Desktop tries to connect.
OAuth 2.1 authorization returns 401 for all requests
You must provide a custom AuthorizationProvider implementation. The framework has no built-in identity provider. Implement the `validate` method to decode and verify tokens from your IdP, and register it with the server before calling `server.run()`.
Frequently Asked Questions about Dedalus Python
What is Dedalus Python?
Dedalus Python is a Model Context Protocol (MCP) server that simple and performant model context protocol framework for python. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Dedalus Python?
Follow the installation instructions on the Dedalus Python GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Dedalus Python?
Dedalus Python works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Dedalus Python free to use?
Yes, Dedalus Python is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Dedalus Python Alternatives — Similar Developer Tools Servers
Looking for alternatives to Dedalus Python? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Dedalus Python in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Dedalus Python?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.