About mcp_sandbox
mcp_sandbox is a collection of experimental MCP server implementations for developers exploring ways to build and test servers. The README describes running individual Python server examples with the MCP Inspector.
Key features
- 01Experimental MCP server implementations
- 02Python-based example servers
- 03Test servers with MCP Inspector
Use cases
- 01Exploring different MCP server implementations
- 02Testing a Python server with MCP Inspector
MCP support
The project contains MCP server examples that can be launched and tested using the MCP Inspector.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMESetup
Install deps python3 -m pip install -r requirements.txt
Install nvm curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash
Install node nvm install --lts
How to use
Start the inspector with npx @modelcontextprotocol/inspector
Go to the web interace on http://127.0.0.1:6274/
Change the command to python3
And the args to servers/echo.py or whichever server you want to test
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.